Part 1 - NN as Regressor

#%tensorflow_version 2.x
import tensorflow as tf
tf.__version__

'2.7.0'

import numpy as np
import pandas as pd
import seaborn as sns
import scipy.stats as stats 
import matplotlib.pyplot as plt
from tensorflow import keras
%matplotlib inline
#Test Train Split
from sklearn.model_selection import train_test_split
#Feature Scaling library
from sklearn.preprocessing import StandardScaler
import pickle
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Flatten, Dense
from tensorflow.keras import regularizers, optimizers
from sklearn.metrics import r2_score
from tensorflow.keras.models import load_model

# Initialize the random number generator
import random
seed = 7
np.random.seed(seed)

# Ignore the warnings
import warnings
warnings.filterwarnings("ignore")

#Read the data as a data frame
mydata = pd.read_csv(r"Signal.xls")
mydata.head(20)

	Parameter 1	Parameter 2	Parameter 3	Parameter 4	Parameter 5	Parameter 6	Parameter 7	Parameter 8	Parameter 9	Parameter 10	Parameter 11	Signal_Strength
0	7.4	0.700	0.00	1.9	0.076	11.0	34.0	0.9978	3.51	0.56	9.4	5
1	7.8	0.880	0.00	2.6	0.098	25.0	67.0	0.9968	3.20	0.68	9.8	5
2	7.8	0.760	0.04	2.3	0.092	15.0	54.0	0.9970	3.26	0.65	9.8	5
3	11.2	0.280	0.56	1.9	0.075	17.0	60.0	0.9980	3.16	0.58	9.8	6
4	7.4	0.700	0.00	1.9	0.076	11.0	34.0	0.9978	3.51	0.56	9.4	5
5	7.4	0.660	0.00	1.8	0.075	13.0	40.0	0.9978	3.51	0.56	9.4	5
6	7.9	0.600	0.06	1.6	0.069	15.0	59.0	0.9964	3.30	0.46	9.4	5
7	7.3	0.650	0.00	1.2	0.065	15.0	21.0	0.9946	3.39	0.47	10.0	7
8	7.8	0.580	0.02	2.0	0.073	9.0	18.0	0.9968	3.36	0.57	9.5	7
9	7.5	0.500	0.36	6.1	0.071	17.0	102.0	0.9978	3.35	0.80	10.5	5
10	6.7	0.580	0.08	1.8	0.097	15.0	65.0	0.9959	3.28	0.54	9.2	5
11	7.5	0.500	0.36	6.1	0.071	17.0	102.0	0.9978	3.35	0.80	10.5	5
12	5.6	0.615	0.00	1.6	0.089	16.0	59.0	0.9943	3.58	0.52	9.9	5
13	7.8	0.610	0.29	1.6	0.114	9.0	29.0	0.9974	3.26	1.56	9.1	5
14	8.9	0.620	0.18	3.8	0.176	52.0	145.0	0.9986	3.16	0.88	9.2	5
15	8.9	0.620	0.19	3.9	0.170	51.0	148.0	0.9986	3.17	0.93	9.2	5
16	8.5	0.280	0.56	1.8	0.092	35.0	103.0	0.9969	3.30	0.75	10.5	7
17	8.1	0.560	0.28	1.7	0.368	16.0	56.0	0.9968	3.11	1.28	9.3	5
18	7.4	0.590	0.08	4.4	0.086	6.0	29.0	0.9974	3.38	0.50	9.0	4
19	7.9	0.320	0.51	1.8	0.341	17.0	56.0	0.9969	3.04	1.08	9.2	6

mydata['Signal_Strength'].unique()

array([5, 6, 7, 4, 8, 3], dtype=int64)

mydata.shape

(1599, 12)

mydata.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1599 entries, 0 to 1598
Data columns (total 12 columns):
 #   Column           Non-Null Count  Dtype  
---  ------           --------------  -----  
 0   Parameter 1      1599 non-null   float64
 1   Parameter 2      1599 non-null   float64
 2   Parameter 3      1599 non-null   float64
 3   Parameter 4      1599 non-null   float64
 4   Parameter 5      1599 non-null   float64
 5   Parameter 6      1599 non-null   float64
 6   Parameter 7      1599 non-null   float64
 7   Parameter 8      1599 non-null   float64
 8   Parameter 9      1599 non-null   float64
 9   Parameter 10     1599 non-null   float64
 10  Parameter 11     1599 non-null   float64
 11  Signal_Strength  1599 non-null   int64  
dtypes: float64(11), int64(1)
memory usage: 150.0 KB

All the parameter values are in float except the Signal strength

# Checking the presence of missing values
null_counts = mydata.isnull().sum()  # This prints the columns with the number of null values they have
print (null_counts)

Parameter 1        0
Parameter 2        0
Parameter 3        0
Parameter 4        0
Parameter 5        0
Parameter 6        0
Parameter 7        0
Parameter 8        0
Parameter 9        0
Parameter 10       0
Parameter 11       0
Signal_Strength    0
dtype: int64

# 5 point summary of numerical attributes
mydata.describe()

	Parameter 1	Parameter 2	Parameter 3	Parameter 4	Parameter 5	Parameter 6	Parameter 7	Parameter 8	Parameter 9	Parameter 10	Parameter 11	Signal_Strength
count	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000
mean	8.319637	0.527821	0.270976	2.538806	0.087467	15.874922	46.467792	0.996747	3.311113	0.658149	10.422983	5.636023
std	1.741096	0.179060	0.194801	1.409928	0.047065	10.460157	32.895324	0.001887	0.154386	0.169507	1.065668	0.807569
min	4.600000	0.120000	0.000000	0.900000	0.012000	1.000000	6.000000	0.990070	2.740000	0.330000	8.400000	3.000000
25%	7.100000	0.390000	0.090000	1.900000	0.070000	7.000000	22.000000	0.995600	3.210000	0.550000	9.500000	5.000000
50%	7.900000	0.520000	0.260000	2.200000	0.079000	14.000000	38.000000	0.996750	3.310000	0.620000	10.200000	6.000000
75%	9.200000	0.640000	0.420000	2.600000	0.090000	21.000000	62.000000	0.997835	3.400000	0.730000	11.100000	6.000000
max	15.900000	1.580000	1.000000	15.500000	0.611000	72.000000	289.000000	1.003690	4.010000	2.000000	14.900000	8.000000

Parameter 3 ranges between 0 and 1.

Maximum value of Parameter 5 is 0.6

Parameter 8 has a very low range between 0.9 and 1.004 Standard deviation is lowest for Parameter 8, it is 0.001887

# studying the distribution of continuous attributes
cols = list(mydata)
for i in np.arange(len(cols)):
    sns.distplot(mydata[cols[i]], color='blue')
    plt.show()
    print('Distribution of ',cols[i])
    print('Mean is:',mydata[cols[i]].mean())
    print('Median is:',mydata[cols[i]].median())
    print('Mode is:',mydata[cols[i]].mode())
    print('Standard deviation is:',mydata[cols[i]].std())
    print('Skewness is:',mydata[cols[i]].skew())
    print('Maximum is:',mydata[cols[i]].max())
    print('Minimum is:',mydata[cols[i]].min())

Distribution of  Parameter 1
Mean is: 8.319637273295838
Median is: 7.9
Mode is: 0    7.2
dtype: float64
Standard deviation is: 1.7410963181277006
Skewness is: 0.9827514413284587
Maximum is: 15.9
Minimum is: 4.6

Distribution of  Parameter 2
Mean is: 0.5278205128205131
Median is: 0.52
Mode is: 0    0.6
dtype: float64
Standard deviation is: 0.17905970415353498
Skewness is: 0.6715925723840199
Maximum is: 1.58
Minimum is: 0.12

Distribution of  Parameter 3
Mean is: 0.2709756097560964
Median is: 0.26
Mode is: 0    0.0
dtype: float64
Standard deviation is: 0.19480113740531785
Skewness is: 0.3183372952546368
Maximum is: 1.0
Minimum is: 0.0

Distribution of  Parameter 4
Mean is: 2.5388055034396517
Median is: 2.2
Mode is: 0    2.0
dtype: float64
Standard deviation is: 1.4099280595072805
Skewness is: 4.54065542590319
Maximum is: 15.5
Minimum is: 0.9

Distribution of  Parameter 5
Mean is: 0.08746654158849257
Median is: 0.079
Mode is: 0    0.08
dtype: float64
Standard deviation is: 0.047065302010090154
Skewness is: 5.680346571971724
Maximum is: 0.611
Minimum is: 0.012

Distribution of  Parameter 6
Mean is: 15.874921826141339
Median is: 14.0
Mode is: 0    6.0
dtype: float64
Standard deviation is: 10.46015696980973
Skewness is: 1.250567293314441
Maximum is: 72.0
Minimum is: 1.0

Distribution of  Parameter 7
Mean is: 46.46779237023139
Median is: 38.0
Mode is: 0    28.0
dtype: float64
Standard deviation is: 32.89532447829901
Skewness is: 1.515531257594554
Maximum is: 289.0
Minimum is: 6.0

Distribution of  Parameter 8
Mean is: 0.9967466791744831
Median is: 0.99675
Mode is: 0    0.9972
dtype: float64
Standard deviation is: 0.0018873339538425559
Skewness is: 0.07128766294927483
Maximum is: 1.00369
Minimum is: 0.99007

Distribution of  Parameter 9
Mean is: 3.311113195747343
Median is: 3.31
Mode is: 0    3.3
dtype: float64
Standard deviation is: 0.15438646490354266
Skewness is: 0.19368349811284427
Maximum is: 4.01
Minimum is: 2.74

Distribution of  Parameter 10
Mean is: 0.6581488430268921
Median is: 0.62
Mode is: 0    0.6
dtype: float64
Standard deviation is: 0.16950697959010977
Skewness is: 2.4286723536602945
Maximum is: 2.0
Minimum is: 0.33

Distribution of  Parameter 11
Mean is: 10.422983114446502
Median is: 10.2
Mode is: 0    9.5
dtype: float64
Standard deviation is: 1.0656675818563965
Skewness is: 0.8608288069184189
Maximum is: 14.9
Minimum is: 8.4

Distribution of  Signal_Strength
Mean is: 5.6360225140712945
Median is: 6.0
Mode is: 0    5
dtype: int64
Standard deviation is: 0.8075694397347023
Skewness is: 0.21780157547366327
Maximum is: 8
Minimum is: 3

fig, ax = plt.subplots()
width = len(mydata['Signal_Strength'].unique()) + 4
fig.set_size_inches(width,4)
ax=sns.countplot(data = mydata, x= 'Signal_Strength') 
plt.title('Distribution of Signal_Strength')


for p in ax.patches: 
    ax.annotate(str((np.round(p.get_height()/len(mydata)*100,decimals=2)))+'%', (p.get_x()+p.get_width()/2., p.get_height()), ha='center', va='center', xytext=(0, 5), textcoords='offset points')

#plt.figure(figsize = (50,50))
sns.pairplot(mydata,diag_kind='kde')
plt.show()

1.Parameter 6 and Parameter 7 are highly correlated with each other and visce versa and they have almost 0 correlation with other Parameters

2.Parameter 1 is positively correlated to Parameter 3 and Parameter 8 and negatively correlated to Parameter 2 and Parameter 9.

3.Parameter 4 is has very low correlation with other Parameters.

fig,ax = plt.subplots(figsize=(15, 10))   
sns.heatmap(mydata.corr(), ax=ax, annot=True, linewidths=0.05, fmt= '.2f',cmap="YlGnBu") 
plt.show()

Since high correlation coefficient value lies between ± 0.50 and ± 1 Parameter 1 is highly correlated with Parameter 3 and Parameter 8, Parameter 9. Parameter 6 and 7 are highly correlated. But since, the correlation is not too high near 0.8 or above not dropping the features.

# Checking the presence of outliers
l = len(mydata)
col = list(mydata.columns)
#col.remove('condition')
for i in np.arange(len(col)):
    sns.boxplot(x= mydata[col[i]], color='cyan')
    plt.show()
    print('Boxplot of ',col[i])
    #calculating the outiers in attribute 
    Q1 = mydata[col[i]].quantile(0.25)
    Q2 = mydata[col[i]].quantile(0.50)
    Q3 = mydata[col[i]].quantile(0.75) 
    IQR = Q3 - Q1
    L_W = (Q1 - 1.5 *IQR)
    U_W = (Q3 + 1.5 *IQR)    
    print('Q1 is : ',Q1)
    print('Q2 is : ',Q2)
    print('Q3 is : ',Q3)
    print('IQR is:',IQR)
    print('Lower Whisker, Upper Whisker : ',L_W,',',U_W)
    bools = (mydata[col[i]] < (Q1 - 1.5 *IQR)) |(mydata[col[i]] > (Q3 + 1.5 * IQR))
    print('Out of ',l,' rows in data, number of outliers are:',bools.sum())   #calculating the number of outliers

Boxplot of  Parameter 1
Q1 is :  7.1
Q2 is :  7.9
Q3 is :  9.2
IQR is: 2.0999999999999996
Lower Whisker, Upper Whisker :  3.95 , 12.349999999999998
Out of  1599  rows in data, number of outliers are: 49

Boxplot of  Parameter 2
Q1 is :  0.39
Q2 is :  0.52
Q3 is :  0.64
IQR is: 0.25
Lower Whisker, Upper Whisker :  0.015000000000000013 , 1.0150000000000001
Out of  1599  rows in data, number of outliers are: 19

Boxplot of  Parameter 3
Q1 is :  0.09
Q2 is :  0.26
Q3 is :  0.42
IQR is: 0.32999999999999996
Lower Whisker, Upper Whisker :  -0.4049999999999999 , 0.9149999999999999
Out of  1599  rows in data, number of outliers are: 1

Boxplot of  Parameter 4
Q1 is :  1.9
Q2 is :  2.2
Q3 is :  2.6
IQR is: 0.7000000000000002
Lower Whisker, Upper Whisker :  0.8499999999999996 , 3.6500000000000004
Out of  1599  rows in data, number of outliers are: 155

Boxplot of  Parameter 5
Q1 is :  0.07
Q2 is :  0.079
Q3 is :  0.09
IQR is: 0.01999999999999999
Lower Whisker, Upper Whisker :  0.04000000000000002 , 0.11999999999999998
Out of  1599  rows in data, number of outliers are: 112

Boxplot of  Parameter 6
Q1 is :  7.0
Q2 is :  14.0
Q3 is :  21.0
IQR is: 14.0
Lower Whisker, Upper Whisker :  -14.0 , 42.0
Out of  1599  rows in data, number of outliers are: 30

Boxplot of  Parameter 7
Q1 is :  22.0
Q2 is :  38.0
Q3 is :  62.0
IQR is: 40.0
Lower Whisker, Upper Whisker :  -38.0 , 122.0
Out of  1599  rows in data, number of outliers are: 55

Boxplot of  Parameter 8
Q1 is :  0.9956
Q2 is :  0.99675
Q3 is :  0.997835
IQR is: 0.002234999999999987
Lower Whisker, Upper Whisker :  0.9922475000000001 , 1.0011875
Out of  1599  rows in data, number of outliers are: 45

Boxplot of  Parameter 9
Q1 is :  3.21
Q2 is :  3.31
Q3 is :  3.4
IQR is: 0.18999999999999995
Lower Whisker, Upper Whisker :  2.925 , 3.6849999999999996
Out of  1599  rows in data, number of outliers are: 35

Boxplot of  Parameter 10
Q1 is :  0.55
Q2 is :  0.62
Q3 is :  0.73
IQR is: 0.17999999999999994
Lower Whisker, Upper Whisker :  0.28000000000000014 , 0.9999999999999999
Out of  1599  rows in data, number of outliers are: 59

Boxplot of  Parameter 11
Q1 is :  9.5
Q2 is :  10.2
Q3 is :  11.1
IQR is: 1.5999999999999996
Lower Whisker, Upper Whisker :  7.1000000000000005 , 13.5
Out of  1599  rows in data, number of outliers are: 13

Boxplot of  Signal_Strength
Q1 is :  5.0
Q2 is :  6.0
Q3 is :  6.0
IQR is: 1.0
Lower Whisker, Upper Whisker :  3.5 , 7.5
Out of  1599  rows in data, number of outliers are: 28

Parameter 4 has the highest number of outliers which is 155.

X = mydata.drop("Signal_Strength", axis=1)
y = mydata['Signal_Strength']

# splitting to create test data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.30, random_state=seed)

print(X_train.shape)
print(X_test.shape)

(1119, 11)
(480, 11)

# splitting to create training and validation data
X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=.20, random_state=seed)

from sklearn.preprocessing import StandardScaler

# Scaling training data
X_Train_S = StandardScaler().fit_transform(X_train)   

# Scaling testing data
X_Test_S = StandardScaler().fit_transform(X_test)     

print(X_train.shape)
print(X_val.shape)
print(X_test.shape)

(895, 11)
(224, 11)
(480, 11)

print(y_train.shape)
print(y_val.shape)
print(y_test.shape)

(895,)
(224,)
(480,)

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Activation, Dense,BatchNormalization, Dropout, LeakyReLU
from tensorflow.keras import optimizers

NN_model_Regressor = Sequential()

# The Input Layer :
NN_model_Regressor.add(Dense(128, kernel_initializer='normal',input_dim = X_train.shape[1], activation='relu'))

# The Hidden Layers :
NN_model_Regressor.add(Dense(64, kernel_initializer='normal',activation='relu'))  # sigmoid, tanh

NN_model_Regressor.add(Dense(32, kernel_initializer='normal'))
NN_model_Regressor.add(LeakyReLU(alpha=0.1))

NN_model_Regressor.add(Dense(16, kernel_initializer='normal'))
NN_model_Regressor.add(LeakyReLU(alpha=0.1))


# The Output Layer :
NN_model_Regressor.add(Dense(1, kernel_initializer='normal'))  # except softmax
NN_model_Regressor.add(LeakyReLU(alpha=0.1))

# Compile the network :
NN_model_Regressor.compile(loss='mse', optimizer='adam',metrics=['accuracy'])
NN_model_Regressor.summary()

Model: "sequential_86"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_364 (Dense)            (None, 128)               1536      
_________________________________________________________________
dense_365 (Dense)            (None, 64)                8256      
_________________________________________________________________
dense_366 (Dense)            (None, 32)                2080      
_________________________________________________________________
leaky_re_lu_164 (LeakyReLU)  (None, 32)                0         
_________________________________________________________________
dense_367 (Dense)            (None, 16)                528       
_________________________________________________________________
leaky_re_lu_165 (LeakyReLU)  (None, 16)                0         
_________________________________________________________________
dense_368 (Dense)            (None, 1)                 17        
_________________________________________________________________
leaky_re_lu_166 (LeakyReLU)  (None, 1)                 0         
=================================================================
Total params: 12,417
Trainable params: 12,417
Non-trainable params: 0
_________________________________________________________________

EPOCH=500
Network_Regressor=NN_model_Regressor.fit(X_Train_S, y_train, validation_data=(X_Test_S,y_test), epochs=EPOCH, batch_size=200)

Epoch 1/500
5/5 [==============================] - 2s 120ms/step - loss: 32.4837 - accuracy: 0.0000e+00 - val_loss: 32.4086 - val_accuracy: 0.0000e+00
Epoch 2/500
5/5 [==============================] - 0s 22ms/step - loss: 32.3190 - accuracy: 0.0000e+00 - val_loss: 32.1814 - val_accuracy: 0.0000e+00
Epoch 3/500
5/5 [==============================] - 0s 18ms/step - loss: 32.0336 - accuracy: 0.0000e+00 - val_loss: 31.7573 - val_accuracy: 0.0000e+00
Epoch 4/500
5/5 [==============================] - 0s 15ms/step - loss: 31.4886 - accuracy: 0.0000e+00 - val_loss: 30.9303 - val_accuracy: 0.0000e+00
Epoch 5/500
5/5 [==============================] - 0s 16ms/step - loss: 30.4223 - accuracy: 0.0000e+00 - val_loss: 29.3253 - val_accuracy: 0.0000e+00
Epoch 6/500
5/5 [==============================] - 0s 16ms/step - loss: 28.4203 - accuracy: 0.0000e+00 - val_loss: 26.3561 - val_accuracy: 0.0000e+00
Epoch 7/500
5/5 [==============================] - 0s 17ms/step - loss: 24.7429 - accuracy: 0.0000e+00 - val_loss: 21.2913 - val_accuracy: 0.0000e+00
Epoch 8/500
5/5 [==============================] - 0s 16ms/step - loss: 18.8562 - accuracy: 0.0000e+00 - val_loss: 13.8197 - val_accuracy: 0.0000e+00
Epoch 9/500
5/5 [==============================] - 0s 17ms/step - loss: 10.8367 - accuracy: 0.0000e+00 - val_loss: 6.0118 - val_accuracy: 0.0000e+00
Epoch 10/500
5/5 [==============================] - 0s 15ms/step - loss: 4.6404 - accuracy: 0.0000e+00 - val_loss: 4.5022 - val_accuracy: 0.0000e+00
Epoch 11/500
5/5 [==============================] - 0s 16ms/step - loss: 4.8536 - accuracy: 0.0000e+00 - val_loss: 5.1978 - val_accuracy: 0.0000e+00
Epoch 12/500
5/5 [==============================] - 0s 18ms/step - loss: 3.9818 - accuracy: 0.0000e+00 - val_loss: 2.9646 - val_accuracy: 0.0000e+00
Epoch 13/500
5/5 [==============================] - 0s 20ms/step - loss: 2.5430 - accuracy: 0.0000e+00 - val_loss: 2.7755 - val_accuracy: 0.0000e+00
Epoch 14/500
5/5 [==============================] - 0s 20ms/step - loss: 2.5323 - accuracy: 0.0000e+00 - val_loss: 2.6219 - val_accuracy: 0.0000e+00
Epoch 15/500
5/5 [==============================] - 0s 20ms/step - loss: 2.2301 - accuracy: 0.0000e+00 - val_loss: 2.2198 - val_accuracy: 0.0000e+00
Epoch 16/500
5/5 [==============================] - 0s 20ms/step - loss: 1.9140 - accuracy: 0.0000e+00 - val_loss: 2.1551 - val_accuracy: 0.0000e+00
Epoch 17/500
5/5 [==============================] - 0s 29ms/step - loss: 1.8204 - accuracy: 0.0000e+00 - val_loss: 2.0674 - val_accuracy: 0.0000e+00
Epoch 18/500
5/5 [==============================] - 0s 25ms/step - loss: 1.7041 - accuracy: 0.0000e+00 - val_loss: 1.9101 - val_accuracy: 0.0000e+00
Epoch 19/500
5/5 [==============================] - 0s 28ms/step - loss: 1.6034 - accuracy: 0.0000e+00 - val_loss: 1.8404 - val_accuracy: 0.0000e+00
Epoch 20/500
5/5 [==============================] - 0s 27ms/step - loss: 1.5381 - accuracy: 0.0000e+00 - val_loss: 1.7752 - val_accuracy: 0.0000e+00
Epoch 21/500
5/5 [==============================] - 0s 23ms/step - loss: 1.4673 - accuracy: 0.0000e+00 - val_loss: 1.7258 - val_accuracy: 0.0000e+00
Epoch 22/500
5/5 [==============================] - 0s 24ms/step - loss: 1.4063 - accuracy: 0.0000e+00 - val_loss: 1.6842 - val_accuracy: 0.0000e+00
Epoch 23/500
5/5 [==============================] - 0s 27ms/step - loss: 1.3534 - accuracy: 0.0000e+00 - val_loss: 1.6244 - val_accuracy: 0.0000e+00
Epoch 24/500
5/5 [==============================] - 0s 27ms/step - loss: 1.3047 - accuracy: 0.0000e+00 - val_loss: 1.5756 - val_accuracy: 0.0000e+00
Epoch 25/500
5/5 [==============================] - 0s 28ms/step - loss: 1.2600 - accuracy: 0.0000e+00 - val_loss: 1.5389 - val_accuracy: 0.0000e+00
Epoch 26/500
5/5 [==============================] - 0s 29ms/step - loss: 1.2162 - accuracy: 0.0000e+00 - val_loss: 1.5025 - val_accuracy: 0.0000e+00
Epoch 27/500
5/5 [==============================] - 0s 16ms/step - loss: 1.1768 - accuracy: 0.0000e+00 - val_loss: 1.4598 - val_accuracy: 0.0000e+00
Epoch 28/500
5/5 [==============================] - 0s 15ms/step - loss: 1.1413 - accuracy: 0.0000e+00 - val_loss: 1.4157 - val_accuracy: 0.0000e+00
Epoch 29/500
5/5 [==============================] - 0s 15ms/step - loss: 1.1065 - accuracy: 0.0000e+00 - val_loss: 1.3823 - val_accuracy: 0.0000e+00
Epoch 30/500
5/5 [==============================] - 0s 16ms/step - loss: 1.0711 - accuracy: 0.0000e+00 - val_loss: 1.3540 - val_accuracy: 0.0000e+00
Epoch 31/500
5/5 [==============================] - 0s 17ms/step - loss: 1.0391 - accuracy: 0.0000e+00 - val_loss: 1.3283 - val_accuracy: 0.0000e+00
Epoch 32/500
5/5 [==============================] - 0s 16ms/step - loss: 1.0081 - accuracy: 0.0000e+00 - val_loss: 1.2983 - val_accuracy: 0.0000e+00
Epoch 33/500
5/5 [==============================] - 0s 39ms/step - loss: 0.9795 - accuracy: 0.0000e+00 - val_loss: 1.2638 - val_accuracy: 0.0000e+00
Epoch 34/500
5/5 [==============================] - 0s 28ms/step - loss: 0.9547 - accuracy: 0.0000e+00 - val_loss: 1.2347 - val_accuracy: 0.0000e+00
Epoch 35/500
5/5 [==============================] - 0s 28ms/step - loss: 0.9279 - accuracy: 0.0000e+00 - val_loss: 1.2122 - val_accuracy: 0.0000e+00
Epoch 36/500
5/5 [==============================] - 0s 33ms/step - loss: 0.9024 - accuracy: 0.0000e+00 - val_loss: 1.1905 - val_accuracy: 0.0000e+00
Epoch 37/500
5/5 [==============================] - 0s 12ms/step - loss: 0.8822 - accuracy: 0.0000e+00 - val_loss: 1.1673 - val_accuracy: 0.0000e+00
Epoch 38/500
5/5 [==============================] - 0s 12ms/step - loss: 0.8602 - accuracy: 0.0000e+00 - val_loss: 1.1404 - val_accuracy: 0.0000e+00
Epoch 39/500
5/5 [==============================] - 0s 12ms/step - loss: 0.8386 - accuracy: 0.0000e+00 - val_loss: 1.1197 - val_accuracy: 0.0000e+00
Epoch 40/500
5/5 [==============================] - 0s 12ms/step - loss: 0.8194 - accuracy: 0.0000e+00 - val_loss: 1.0965 - val_accuracy: 0.0000e+00
Epoch 41/500
5/5 [==============================] - 0s 13ms/step - loss: 0.8009 - accuracy: 0.0000e+00 - val_loss: 1.0738 - val_accuracy: 0.0000e+00
Epoch 42/500
5/5 [==============================] - 0s 16ms/step - loss: 0.7817 - accuracy: 0.0000e+00 - val_loss: 1.0561 - val_accuracy: 0.0000e+00
Epoch 43/500
5/5 [==============================] - 0s 20ms/step - loss: 0.7664 - accuracy: 0.0000e+00 - val_loss: 1.0376 - val_accuracy: 0.0000e+00
Epoch 44/500
5/5 [==============================] - 0s 28ms/step - loss: 0.7489 - accuracy: 0.0000e+00 - val_loss: 1.0159 - val_accuracy: 0.0000e+00
Epoch 45/500
5/5 [==============================] - 0s 25ms/step - loss: 0.7361 - accuracy: 0.0000e+00 - val_loss: 0.9991 - val_accuracy: 0.0000e+00
Epoch 46/500
5/5 [==============================] - 0s 18ms/step - loss: 0.7199 - accuracy: 0.0000e+00 - val_loss: 0.9906 - val_accuracy: 0.0000e+00
Epoch 47/500
5/5 [==============================] - 0s 18ms/step - loss: 0.7077 - accuracy: 0.0000e+00 - val_loss: 0.9729 - val_accuracy: 0.0000e+00
Epoch 48/500
5/5 [==============================] - 0s 17ms/step - loss: 0.6946 - accuracy: 0.0000e+00 - val_loss: 0.9530 - val_accuracy: 0.0000e+00
Epoch 49/500
5/5 [==============================] - 0s 18ms/step - loss: 0.6813 - accuracy: 0.0000e+00 - val_loss: 0.9397 - val_accuracy: 0.0000e+00
Epoch 50/500
5/5 [==============================] - 0s 18ms/step - loss: 0.6697 - accuracy: 0.0000e+00 - val_loss: 0.9208 - val_accuracy: 0.0000e+00
Epoch 51/500
5/5 [==============================] - 0s 26ms/step - loss: 0.6574 - accuracy: 0.0000e+00 - val_loss: 0.9099 - val_accuracy: 0.0000e+00
Epoch 52/500
5/5 [==============================] - 0s 28ms/step - loss: 0.6465 - accuracy: 0.0000e+00 - val_loss: 0.8957 - val_accuracy: 0.0000e+00
Epoch 53/500
5/5 [==============================] - 0s 27ms/step - loss: 0.6367 - accuracy: 0.0000e+00 - val_loss: 0.8837 - val_accuracy: 0.0000e+00
Epoch 54/500
5/5 [==============================] - 0s 28ms/step - loss: 0.6286 - accuracy: 0.0000e+00 - val_loss: 0.8783 - val_accuracy: 0.0000e+00
Epoch 55/500
5/5 [==============================] - 0s 28ms/step - loss: 0.6197 - accuracy: 0.0000e+00 - val_loss: 0.8639 - val_accuracy: 0.0000e+00
Epoch 56/500
5/5 [==============================] - 0s 31ms/step - loss: 0.6121 - accuracy: 0.0000e+00 - val_loss: 0.8498 - val_accuracy: 0.0000e+00
Epoch 57/500
5/5 [==============================] - 0s 29ms/step - loss: 0.6023 - accuracy: 0.0000e+00 - val_loss: 0.8460 - val_accuracy: 0.0000e+00
Epoch 58/500
5/5 [==============================] - 0s 12ms/step - loss: 0.5923 - accuracy: 0.0000e+00 - val_loss: 0.8298 - val_accuracy: 0.0000e+00
Epoch 59/500
5/5 [==============================] - 0s 11ms/step - loss: 0.5835 - accuracy: 0.0000e+00 - val_loss: 0.8192 - val_accuracy: 0.0000e+00
Epoch 60/500
5/5 [==============================] - 0s 18ms/step - loss: 0.5766 - accuracy: 0.0000e+00 - val_loss: 0.8070 - val_accuracy: 0.0000e+00
Epoch 61/500
5/5 [==============================] - 0s 23ms/step - loss: 0.5700 - accuracy: 0.0000e+00 - val_loss: 0.7990 - val_accuracy: 0.0000e+00
Epoch 62/500
5/5 [==============================] - 0s 23ms/step - loss: 0.5620 - accuracy: 0.0000e+00 - val_loss: 0.7910 - val_accuracy: 0.0000e+00
Epoch 63/500
5/5 [==============================] - 0s 16ms/step - loss: 0.5553 - accuracy: 0.0000e+00 - val_loss: 0.7816 - val_accuracy: 0.0000e+00
Epoch 64/500
5/5 [==============================] - 0s 15ms/step - loss: 0.5506 - accuracy: 0.0000e+00 - val_loss: 0.7714 - val_accuracy: 0.0000e+00
Epoch 65/500
5/5 [==============================] - 0s 14ms/step - loss: 0.5455 - accuracy: 0.0000e+00 - val_loss: 0.7693 - val_accuracy: 0.0000e+00
Epoch 66/500
5/5 [==============================] - 0s 16ms/step - loss: 0.5375 - accuracy: 0.0000e+00 - val_loss: 0.7582 - val_accuracy: 0.0000e+00
Epoch 67/500
5/5 [==============================] - 0s 16ms/step - loss: 0.5323 - accuracy: 0.0000e+00 - val_loss: 0.7491 - val_accuracy: 0.0000e+00
Epoch 68/500
5/5 [==============================] - 0s 16ms/step - loss: 0.5287 - accuracy: 0.0000e+00 - val_loss: 0.7451 - val_accuracy: 0.0000e+00
Epoch 69/500
5/5 [==============================] - 0s 16ms/step - loss: 0.5223 - accuracy: 0.0000e+00 - val_loss: 0.7384 - val_accuracy: 0.0000e+00
Epoch 70/500
5/5 [==============================] - 0s 21ms/step - loss: 0.5175 - accuracy: 0.0000e+00 - val_loss: 0.7309 - val_accuracy: 0.0000e+00
Epoch 71/500
5/5 [==============================] - 0s 16ms/step - loss: 0.5146 - accuracy: 0.0000e+00 - val_loss: 0.7263 - val_accuracy: 0.0000e+00
Epoch 72/500
5/5 [==============================] - 0s 15ms/step - loss: 0.5090 - accuracy: 0.0000e+00 - val_loss: 0.7161 - val_accuracy: 0.0000e+00
Epoch 73/500
5/5 [==============================] - 0s 14ms/step - loss: 0.5047 - accuracy: 0.0000e+00 - val_loss: 0.7102 - val_accuracy: 0.0000e+00
Epoch 74/500
5/5 [==============================] - 0s 13ms/step - loss: 0.4995 - accuracy: 0.0000e+00 - val_loss: 0.7081 - val_accuracy: 0.0000e+00
Epoch 75/500
5/5 [==============================] - 0s 16ms/step - loss: 0.4987 - accuracy: 0.0000e+00 - val_loss: 0.7048 - val_accuracy: 0.0000e+00
Epoch 76/500
5/5 [==============================] - 0s 16ms/step - loss: 0.4911 - accuracy: 0.0000e+00 - val_loss: 0.6927 - val_accuracy: 0.0000e+00
Epoch 77/500
5/5 [==============================] - 0s 16ms/step - loss: 0.4909 - accuracy: 0.0000e+00 - val_loss: 0.6878 - val_accuracy: 0.0000e+00
Epoch 78/500
5/5 [==============================] - 0s 16ms/step - loss: 0.4912 - accuracy: 0.0000e+00 - val_loss: 0.6924 - val_accuracy: 0.0000e+00
Epoch 79/500
5/5 [==============================] - 0s 16ms/step - loss: 0.4840 - accuracy: 0.0000e+00 - val_loss: 0.6761 - val_accuracy: 0.0000e+00
Epoch 80/500
5/5 [==============================] - 0s 26ms/step - loss: 0.4797 - accuracy: 0.0000e+00 - val_loss: 0.6722 - val_accuracy: 0.0000e+00
Epoch 81/500
5/5 [==============================] - 0s 27ms/step - loss: 0.4766 - accuracy: 0.0000e+00 - val_loss: 0.6690 - val_accuracy: 0.0000e+00
Epoch 82/500
5/5 [==============================] - 0s 35ms/step - loss: 0.4731 - accuracy: 0.0000e+00 - val_loss: 0.6657 - val_accuracy: 0.0000e+00
Epoch 83/500
5/5 [==============================] - 0s 17ms/step - loss: 0.4693 - accuracy: 0.0000e+00 - val_loss: 0.6577 - val_accuracy: 0.0000e+00
Epoch 84/500
5/5 [==============================] - 0s 13ms/step - loss: 0.4692 - accuracy: 0.0000e+00 - val_loss: 0.6540 - val_accuracy: 0.0000e+00
Epoch 85/500
5/5 [==============================] - 0s 16ms/step - loss: 0.4675 - accuracy: 0.0000e+00 - val_loss: 0.6558 - val_accuracy: 0.0000e+00
Epoch 86/500
5/5 [==============================] - 0s 30ms/step - loss: 0.4631 - accuracy: 0.0000e+00 - val_loss: 0.6493 - val_accuracy: 0.0000e+00
Epoch 87/500
5/5 [==============================] - 0s 29ms/step - loss: 0.4600 - accuracy: 0.0000e+00 - val_loss: 0.6430 - val_accuracy: 0.0000e+00
Epoch 88/500
5/5 [==============================] - 0s 29ms/step - loss: 0.4580 - accuracy: 0.0000e+00 - val_loss: 0.6416 - val_accuracy: 0.0000e+00
Epoch 89/500
5/5 [==============================] - 0s 29ms/step - loss: 0.4568 - accuracy: 0.0000e+00 - val_loss: 0.6404 - val_accuracy: 0.0000e+00
Epoch 90/500
5/5 [==============================] - 0s 29ms/step - loss: 0.4532 - accuracy: 0.0000e+00 - val_loss: 0.6350 - val_accuracy: 0.0000e+00
Epoch 91/500
5/5 [==============================] - 0s 30ms/step - loss: 0.4514 - accuracy: 0.0000e+00 - val_loss: 0.6309 - val_accuracy: 0.0000e+00
Epoch 92/500
5/5 [==============================] - 0s 16ms/step - loss: 0.4503 - accuracy: 0.0000e+00 - val_loss: 0.6253 - val_accuracy: 0.0000e+00
Epoch 93/500
5/5 [==============================] - 0s 15ms/step - loss: 0.4460 - accuracy: 0.0000e+00 - val_loss: 0.6294 - val_accuracy: 0.0000e+00
Epoch 94/500
5/5 [==============================] - 0s 34ms/step - loss: 0.4480 - accuracy: 0.0000e+00 - val_loss: 0.6210 - val_accuracy: 0.0000e+00
Epoch 95/500
5/5 [==============================] - 0s 28ms/step - loss: 0.4453 - accuracy: 0.0000e+00 - val_loss: 0.6165 - val_accuracy: 0.0000e+00
Epoch 96/500
5/5 [==============================] - 0s 28ms/step - loss: 0.4420 - accuracy: 0.0000e+00 - val_loss: 0.6189 - val_accuracy: 0.0000e+00
Epoch 97/500
5/5 [==============================] - 0s 28ms/step - loss: 0.4457 - accuracy: 0.0000e+00 - val_loss: 0.6265 - val_accuracy: 0.0000e+00
Epoch 98/500
5/5 [==============================] - 0s 33ms/step - loss: 0.4410 - accuracy: 0.0000e+00 - val_loss: 0.6099 - val_accuracy: 0.0000e+00
Epoch 99/500
5/5 [==============================] - 0s 35ms/step - loss: 0.4381 - accuracy: 0.0000e+00 - val_loss: 0.6085 - val_accuracy: 0.0000e+00
Epoch 100/500
5/5 [==============================] - 0s 14ms/step - loss: 0.4370 - accuracy: 0.0000e+00 - val_loss: 0.6087 - val_accuracy: 0.0000e+00
Epoch 101/500
5/5 [==============================] - 0s 11ms/step - loss: 0.4339 - accuracy: 0.0000e+00 - val_loss: 0.6018 - val_accuracy: 0.0000e+00
Epoch 102/500
5/5 [==============================] - 0s 11ms/step - loss: 0.4339 - accuracy: 0.0000e+00 - val_loss: 0.5986 - val_accuracy: 0.0000e+00
Epoch 103/500
5/5 [==============================] - 0s 25ms/step - loss: 0.4312 - accuracy: 0.0000e+00 - val_loss: 0.5976 - val_accuracy: 0.0000e+00
Epoch 104/500
5/5 [==============================] - 0s 29ms/step - loss: 0.4291 - accuracy: 0.0000e+00 - val_loss: 0.6000 - val_accuracy: 0.0000e+00
Epoch 105/500
5/5 [==============================] - 0s 32ms/step - loss: 0.4282 - accuracy: 0.0000e+00 - val_loss: 0.5910 - val_accuracy: 0.0000e+00
Epoch 106/500
5/5 [==============================] - 0s 33ms/step - loss: 0.4279 - accuracy: 0.0000e+00 - val_loss: 0.5870 - val_accuracy: 0.0000e+00
Epoch 107/500
5/5 [==============================] - 0s 30ms/step - loss: 0.4260 - accuracy: 0.0000e+00 - val_loss: 0.5904 - val_accuracy: 0.0000e+00
Epoch 108/500
5/5 [==============================] - 0s 28ms/step - loss: 0.4269 - accuracy: 0.0000e+00 - val_loss: 0.5922 - val_accuracy: 0.0000e+00
Epoch 109/500
5/5 [==============================] - 0s 31ms/step - loss: 0.4243 - accuracy: 0.0000e+00 - val_loss: 0.5862 - val_accuracy: 0.0000e+00
Epoch 110/500
5/5 [==============================] - 0s 13ms/step - loss: 0.4224 - accuracy: 0.0000e+00 - val_loss: 0.5842 - val_accuracy: 0.0000e+00
Epoch 111/500
5/5 [==============================] - 0s 13ms/step - loss: 0.4219 - accuracy: 0.0000e+00 - val_loss: 0.5853 - val_accuracy: 0.0000e+00
Epoch 112/500
5/5 [==============================] - 0s 25ms/step - loss: 0.4216 - accuracy: 0.0000e+00 - val_loss: 0.5796 - val_accuracy: 0.0000e+00
Epoch 113/500
5/5 [==============================] - 0s 31ms/step - loss: 0.4197 - accuracy: 0.0000e+00 - val_loss: 0.5782 - val_accuracy: 0.0000e+00
Epoch 114/500
5/5 [==============================] - 0s 29ms/step - loss: 0.4179 - accuracy: 0.0000e+00 - val_loss: 0.5783 - val_accuracy: 0.0000e+00
Epoch 115/500
5/5 [==============================] - 0s 27ms/step - loss: 0.4165 - accuracy: 0.0000e+00 - val_loss: 0.5761 - val_accuracy: 0.0000e+00
Epoch 116/500
5/5 [==============================] - 0s 34ms/step - loss: 0.4161 - accuracy: 0.0000e+00 - val_loss: 0.5732 - val_accuracy: 0.0000e+00
Epoch 117/500
5/5 [==============================] - 0s 32ms/step - loss: 0.4156 - accuracy: 0.0000e+00 - val_loss: 0.5693 - val_accuracy: 0.0000e+00
Epoch 118/500
5/5 [==============================] - 0s 24ms/step - loss: 0.4167 - accuracy: 0.0000e+00 - val_loss: 0.5702 - val_accuracy: 0.0000e+00
Epoch 119/500
5/5 [==============================] - 0s 12ms/step - loss: 0.4138 - accuracy: 0.0000e+00 - val_loss: 0.5697 - val_accuracy: 0.0000e+00
Epoch 120/500
5/5 [==============================] - 0s 34ms/step - loss: 0.4125 - accuracy: 0.0000e+00 - val_loss: 0.5669 - val_accuracy: 0.0000e+00
Epoch 121/500
5/5 [==============================] - 0s 32ms/step - loss: 0.4125 - accuracy: 0.0000e+00 - val_loss: 0.5683 - val_accuracy: 0.0000e+00
Epoch 122/500
5/5 [==============================] - 0s 32ms/step - loss: 0.4117 - accuracy: 0.0000e+00 - val_loss: 0.5684 - val_accuracy: 0.0000e+00
Epoch 123/500
5/5 [==============================] - 0s 28ms/step - loss: 0.4123 - accuracy: 0.0000e+00 - val_loss: 0.5639 - val_accuracy: 0.0000e+00
Epoch 124/500
5/5 [==============================] - 0s 28ms/step - loss: 0.4100 - accuracy: 0.0000e+00 - val_loss: 0.5644 - val_accuracy: 0.0000e+00
Epoch 125/500
5/5 [==============================] - 0s 29ms/step - loss: 0.4094 - accuracy: 0.0000e+00 - val_loss: 0.5652 - val_accuracy: 0.0000e+00
Epoch 126/500
5/5 [==============================] - 0s 32ms/step - loss: 0.4098 - accuracy: 0.0000e+00 - val_loss: 0.5605 - val_accuracy: 0.0000e+00
Epoch 127/500
5/5 [==============================] - 0s 30ms/step - loss: 0.4091 - accuracy: 0.0000e+00 - val_loss: 0.5565 - val_accuracy: 0.0000e+00
Epoch 128/500
5/5 [==============================] - 0s 27ms/step - loss: 0.4062 - accuracy: 0.0000e+00 - val_loss: 0.5614 - val_accuracy: 0.0000e+00
Epoch 129/500
5/5 [==============================] - 0s 27ms/step - loss: 0.4074 - accuracy: 0.0000e+00 - val_loss: 0.5637 - val_accuracy: 0.0000e+00
Epoch 130/500
5/5 [==============================] - 0s 31ms/step - loss: 0.4064 - accuracy: 0.0000e+00 - val_loss: 0.5575 - val_accuracy: 0.0000e+00
Epoch 131/500
5/5 [==============================] - 0s 32ms/step - loss: 0.4071 - accuracy: 0.0000e+00 - val_loss: 0.5564 - val_accuracy: 0.0000e+00
Epoch 132/500
5/5 [==============================] - 0s 31ms/step - loss: 0.4057 - accuracy: 0.0000e+00 - val_loss: 0.5589 - val_accuracy: 0.0000e+00
Epoch 133/500
5/5 [==============================] - 0s 26ms/step - loss: 0.4058 - accuracy: 0.0000e+00 - val_loss: 0.5558 - val_accuracy: 0.0000e+00
Epoch 134/500
5/5 [==============================] - 0s 11ms/step - loss: 0.4032 - accuracy: 0.0000e+00 - val_loss: 0.5529 - val_accuracy: 0.0000e+00
Epoch 135/500
5/5 [==============================] - 0s 11ms/step - loss: 0.4032 - accuracy: 0.0000e+00 - val_loss: 0.5516 - val_accuracy: 0.0000e+00
Epoch 136/500
5/5 [==============================] - 0s 12ms/step - loss: 0.4033 - accuracy: 0.0000e+00 - val_loss: 0.5530 - val_accuracy: 0.0000e+00
Epoch 137/500
5/5 [==============================] - 0s 20ms/step - loss: 0.4021 - accuracy: 0.0000e+00 - val_loss: 0.5479 - val_accuracy: 0.0000e+00
Epoch 138/500
5/5 [==============================] - 0s 29ms/step - loss: 0.4019 - accuracy: 0.0000e+00 - val_loss: 0.5481 - val_accuracy: 0.0000e+00
Epoch 139/500
5/5 [==============================] - 0s 27ms/step - loss: 0.4041 - accuracy: 0.0000e+00 - val_loss: 0.5516 - val_accuracy: 0.0000e+00
Epoch 140/500
5/5 [==============================] - 0s 29ms/step - loss: 0.4016 - accuracy: 0.0000e+00 - val_loss: 0.5463 - val_accuracy: 0.0000e+00
Epoch 141/500
5/5 [==============================] - 0s 28ms/step - loss: 0.4025 - accuracy: 0.0000e+00 - val_loss: 0.5510 - val_accuracy: 0.0000e+00
Epoch 142/500
5/5 [==============================] - 0s 28ms/step - loss: 0.3997 - accuracy: 0.0000e+00 - val_loss: 0.5489 - val_accuracy: 0.0000e+00
Epoch 143/500
5/5 [==============================] - 0s 32ms/step - loss: 0.3992 - accuracy: 0.0000e+00 - val_loss: 0.5453 - val_accuracy: 0.0000e+00
Epoch 144/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3980 - accuracy: 0.0000e+00 - val_loss: 0.5458 - val_accuracy: 0.0000e+00
Epoch 145/500
5/5 [==============================] - 0s 10ms/step - loss: 0.3990 - accuracy: 0.0000e+00 - val_loss: 0.5449 - val_accuracy: 0.0000e+00
Epoch 146/500
5/5 [==============================] - 0s 10ms/step - loss: 0.4018 - accuracy: 0.0000e+00 - val_loss: 0.5389 - val_accuracy: 0.0000e+00
Epoch 147/500
5/5 [==============================] - 0s 13ms/step - loss: 0.4003 - accuracy: 0.0000e+00 - val_loss: 0.5443 - val_accuracy: 0.0000e+00
Epoch 148/500
5/5 [==============================] - 0s 28ms/step - loss: 0.3988 - accuracy: 0.0000e+00 - val_loss: 0.5390 - val_accuracy: 0.0000e+00
Epoch 149/500
5/5 [==============================] - 0s 30ms/step - loss: 0.3969 - accuracy: 0.0000e+00 - val_loss: 0.5420 - val_accuracy: 0.0000e+00
Epoch 150/500
5/5 [==============================] - 0s 28ms/step - loss: 0.3952 - accuracy: 0.0000e+00 - val_loss: 0.5403 - val_accuracy: 0.0000e+00
Epoch 151/500
5/5 [==============================] - 0s 29ms/step - loss: 0.3966 - accuracy: 0.0000e+00 - val_loss: 0.5389 - val_accuracy: 0.0000e+00
Epoch 152/500
5/5 [==============================] - 0s 32ms/step - loss: 0.3951 - accuracy: 0.0000e+00 - val_loss: 0.5356 - val_accuracy: 0.0000e+00
Epoch 153/500
5/5 [==============================] - 0s 32ms/step - loss: 0.3948 - accuracy: 0.0000e+00 - val_loss: 0.5394 - val_accuracy: 0.0000e+00
Epoch 154/500
5/5 [==============================] - 0s 14ms/step - loss: 0.3949 - accuracy: 0.0000e+00 - val_loss: 0.5376 - val_accuracy: 0.0000e+00
Epoch 155/500
5/5 [==============================] - 0s 14ms/step - loss: 0.3943 - accuracy: 0.0000e+00 - val_loss: 0.5343 - val_accuracy: 0.0000e+00
Epoch 156/500
5/5 [==============================] - 0s 14ms/step - loss: 0.3945 - accuracy: 0.0000e+00 - val_loss: 0.5375 - val_accuracy: 0.0000e+00
Epoch 157/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3931 - accuracy: 0.0000e+00 - val_loss: 0.5322 - val_accuracy: 0.0000e+00
Epoch 158/500
5/5 [==============================] - 0s 28ms/step - loss: 0.3941 - accuracy: 0.0000e+00 - val_loss: 0.5328 - val_accuracy: 0.0000e+00
Epoch 159/500
5/5 [==============================] - 0s 29ms/step - loss: 0.3947 - accuracy: 0.0000e+00 - val_loss: 0.5374 - val_accuracy: 0.0000e+00
Epoch 160/500
5/5 [==============================] - 0s 31ms/step - loss: 0.3930 - accuracy: 0.0000e+00 - val_loss: 0.5384 - val_accuracy: 0.0000e+00
Epoch 161/500
5/5 [==============================] - 0s 27ms/step - loss: 0.3943 - accuracy: 0.0000e+00 - val_loss: 0.5317 - val_accuracy: 0.0000e+00
Epoch 162/500
5/5 [==============================] - 0s 33ms/step - loss: 0.3930 - accuracy: 0.0000e+00 - val_loss: 0.5323 - val_accuracy: 0.0000e+00
Epoch 163/500
5/5 [==============================] - 0s 24ms/step - loss: 0.3913 - accuracy: 0.0000e+00 - val_loss: 0.5332 - val_accuracy: 0.0000e+00
Epoch 164/500
5/5 [==============================] - 0s 21ms/step - loss: 0.3917 - accuracy: 0.0000e+00 - val_loss: 0.5333 - val_accuracy: 0.0000e+00
Epoch 165/500
5/5 [==============================] - 0s 26ms/step - loss: 0.3916 - accuracy: 0.0000e+00 - val_loss: 0.5318 - val_accuracy: 0.0000e+00
Epoch 166/500
5/5 [==============================] - 0s 28ms/step - loss: 0.3894 - accuracy: 0.0000e+00 - val_loss: 0.5307 - val_accuracy: 0.0000e+00
Epoch 167/500
5/5 [==============================] - 0s 27ms/step - loss: 0.3927 - accuracy: 0.0000e+00 - val_loss: 0.5303 - val_accuracy: 0.0000e+00
Epoch 168/500
5/5 [==============================] - 0s 27ms/step - loss: 0.3884 - accuracy: 0.0000e+00 - val_loss: 0.5315 - val_accuracy: 0.0000e+00
Epoch 169/500
5/5 [==============================] - 0s 28ms/step - loss: 0.3902 - accuracy: 0.0000e+00 - val_loss: 0.5293 - val_accuracy: 0.0000e+00
Epoch 170/500
5/5 [==============================] - 0s 26ms/step - loss: 0.3887 - accuracy: 0.0000e+00 - val_loss: 0.5265 - val_accuracy: 0.0000e+00
Epoch 171/500
5/5 [==============================] - 0s 20ms/step - loss: 0.3878 - accuracy: 0.0000e+00 - val_loss: 0.5267 - val_accuracy: 0.0000e+00
Epoch 172/500
5/5 [==============================] - 0s 12ms/step - loss: 0.3874 - accuracy: 0.0000e+00 - val_loss: 0.5287 - val_accuracy: 0.0000e+00
Epoch 173/500
5/5 [==============================] - 0s 13ms/step - loss: 0.3879 - accuracy: 0.0000e+00 - val_loss: 0.5320 - val_accuracy: 0.0000e+00
Epoch 174/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3886 - accuracy: 0.0000e+00 - val_loss: 0.5290 - val_accuracy: 0.0000e+00
Epoch 175/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3879 - accuracy: 0.0000e+00 - val_loss: 0.5346 - val_accuracy: 0.0000e+00
Epoch 176/500
5/5 [==============================] - 0s 18ms/step - loss: 0.3877 - accuracy: 0.0000e+00 - val_loss: 0.5258 - val_accuracy: 0.0000e+00
Epoch 177/500
5/5 [==============================] - 0s 19ms/step - loss: 0.3859 - accuracy: 0.0000e+00 - val_loss: 0.5265 - val_accuracy: 0.0000e+00
Epoch 178/500
5/5 [==============================] - 0s 20ms/step - loss: 0.3864 - accuracy: 0.0000e+00 - val_loss: 0.5271 - val_accuracy: 0.0000e+00
Epoch 179/500
5/5 [==============================] - 0s 20ms/step - loss: 0.3854 - accuracy: 0.0000e+00 - val_loss: 0.5232 - val_accuracy: 0.0000e+00
Epoch 180/500
5/5 [==============================] - 0s 20ms/step - loss: 0.3853 - accuracy: 0.0000e+00 - val_loss: 0.5228 - val_accuracy: 0.0000e+00
Epoch 181/500
5/5 [==============================] - 0s 19ms/step - loss: 0.3853 - accuracy: 0.0000e+00 - val_loss: 0.5256 - val_accuracy: 0.0000e+00
Epoch 182/500
5/5 [==============================] - 0s 19ms/step - loss: 0.3861 - accuracy: 0.0000e+00 - val_loss: 0.5213 - val_accuracy: 0.0000e+00
Epoch 183/500
5/5 [==============================] - 0s 21ms/step - loss: 0.3857 - accuracy: 0.0000e+00 - val_loss: 0.5227 - val_accuracy: 0.0000e+00
Epoch 184/500
5/5 [==============================] - 0s 21ms/step - loss: 0.3861 - accuracy: 0.0000e+00 - val_loss: 0.5238 - val_accuracy: 0.0000e+00
Epoch 185/500
5/5 [==============================] - 0s 21ms/step - loss: 0.3897 - accuracy: 0.0000e+00 - val_loss: 0.5258 - val_accuracy: 0.0000e+00
Epoch 186/500
5/5 [==============================] - 0s 21ms/step - loss: 0.3863 - accuracy: 0.0000e+00 - val_loss: 0.5252 - val_accuracy: 0.0000e+00
Epoch 187/500
5/5 [==============================] - 0s 27ms/step - loss: 0.3871 - accuracy: 0.0000e+00 - val_loss: 0.5268 - val_accuracy: 0.0000e+00
Epoch 188/500
5/5 [==============================] - 0s 28ms/step - loss: 0.3867 - accuracy: 0.0000e+00 - val_loss: 0.5238 - val_accuracy: 0.0000e+00
Epoch 189/500
5/5 [==============================] - 0s 27ms/step - loss: 0.3856 - accuracy: 0.0000e+00 - val_loss: 0.5226 - val_accuracy: 0.0000e+00
Epoch 190/500
5/5 [==============================] - 0s 27ms/step - loss: 0.3831 - accuracy: 0.0000e+00 - val_loss: 0.5201 - val_accuracy: 0.0000e+00
Epoch 191/500
5/5 [==============================] - 0s 27ms/step - loss: 0.3838 - accuracy: 0.0000e+00 - val_loss: 0.5200 - val_accuracy: 0.0000e+00
Epoch 192/500
5/5 [==============================] - 0s 16ms/step - loss: 0.3831 - accuracy: 0.0000e+00 - val_loss: 0.5274 - val_accuracy: 0.0000e+00
Epoch 193/500
5/5 [==============================] - 0s 19ms/step - loss: 0.3834 - accuracy: 0.0000e+00 - val_loss: 0.5199 - val_accuracy: 0.0000e+00
Epoch 194/500
5/5 [==============================] - 0s 10ms/step - loss: 0.3838 - accuracy: 0.0000e+00 - val_loss: 0.5190 - val_accuracy: 0.0000e+00
Epoch 195/500
5/5 [==============================] - 0s 10ms/step - loss: 0.3823 - accuracy: 0.0000e+00 - val_loss: 0.5220 - val_accuracy: 0.0000e+00
Epoch 196/500
5/5 [==============================] - 0s 11ms/step - loss: 0.3820 - accuracy: 0.0000e+00 - val_loss: 0.5202 - val_accuracy: 0.0000e+00
Epoch 197/500
5/5 [==============================] - 0s 10ms/step - loss: 0.3814 - accuracy: 0.0000e+00 - val_loss: 0.5186 - val_accuracy: 0.0000e+00
Epoch 198/500
5/5 [==============================] - 0s 11ms/step - loss: 0.3824 - accuracy: 0.0000e+00 - val_loss: 0.5162 - val_accuracy: 0.0000e+00
Epoch 199/500
5/5 [==============================] - 0s 12ms/step - loss: 0.3828 - accuracy: 0.0000e+00 - val_loss: 0.5212 - val_accuracy: 0.0000e+00
Epoch 200/500
5/5 [==============================] - 0s 14ms/step - loss: 0.3825 - accuracy: 0.0000e+00 - val_loss: 0.5195 - val_accuracy: 0.0000e+00
Epoch 201/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3817 - accuracy: 0.0000e+00 - val_loss: 0.5212 - val_accuracy: 0.0000e+00
Epoch 202/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3836 - accuracy: 0.0000e+00 - val_loss: 0.5202 - val_accuracy: 0.0000e+00
Epoch 203/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3823 - accuracy: 0.0000e+00 - val_loss: 0.5194 - val_accuracy: 0.0000e+00
Epoch 204/500
5/5 [==============================] - 0s 16ms/step - loss: 0.3825 - accuracy: 0.0000e+00 - val_loss: 0.5203 - val_accuracy: 0.0000e+00
Epoch 205/500
5/5 [==============================] - 0s 17ms/step - loss: 0.3779 - accuracy: 0.0000e+00 - val_loss: 0.5201 - val_accuracy: 0.0000e+00
Epoch 206/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3813 - accuracy: 0.0000e+00 - val_loss: 0.5202 - val_accuracy: 0.0000e+00
Epoch 207/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3815 - accuracy: 0.0000e+00 - val_loss: 0.5258 - val_accuracy: 0.0000e+00
Epoch 208/500
5/5 [==============================] - 0s 14ms/step - loss: 0.3815 - accuracy: 0.0000e+00 - val_loss: 0.5200 - val_accuracy: 0.0000e+00
Epoch 209/500
5/5 [==============================] - 0s 16ms/step - loss: 0.3792 - accuracy: 0.0000e+00 - val_loss: 0.5252 - val_accuracy: 0.0000e+00
Epoch 210/500
5/5 [==============================] - 0s 16ms/step - loss: 0.3799 - accuracy: 0.0000e+00 - val_loss: 0.5191 - val_accuracy: 0.0000e+00
Epoch 211/500
5/5 [==============================] - 0s 16ms/step - loss: 0.3775 - accuracy: 0.0000e+00 - val_loss: 0.5169 - val_accuracy: 0.0000e+00
Epoch 212/500
5/5 [==============================] - 0s 16ms/step - loss: 0.3773 - accuracy: 0.0000e+00 - val_loss: 0.5190 - val_accuracy: 0.0000e+00
Epoch 213/500
5/5 [==============================] - 0s 16ms/step - loss: 0.3773 - accuracy: 0.0000e+00 - val_loss: 0.5142 - val_accuracy: 0.0000e+00
Epoch 214/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3777 - accuracy: 0.0000e+00 - val_loss: 0.5173 - val_accuracy: 0.0000e+00
Epoch 215/500
5/5 [==============================] - 0s 18ms/step - loss: 0.3758 - accuracy: 0.0000e+00 - val_loss: 0.5211 - val_accuracy: 0.0000e+00
Epoch 216/500
5/5 [==============================] - 0s 26ms/step - loss: 0.3768 - accuracy: 0.0000e+00 - val_loss: 0.5156 - val_accuracy: 0.0000e+00
Epoch 217/500
5/5 [==============================] - 0s 29ms/step - loss: 0.3762 - accuracy: 0.0000e+00 - val_loss: 0.5145 - val_accuracy: 0.0000e+00
Epoch 218/500
5/5 [==============================] - 0s 29ms/step - loss: 0.3751 - accuracy: 0.0000e+00 - val_loss: 0.5155 - val_accuracy: 0.0000e+00
Epoch 219/500
5/5 [==============================] - 0s 29ms/step - loss: 0.3761 - accuracy: 0.0000e+00 - val_loss: 0.5133 - val_accuracy: 0.0000e+00
Epoch 220/500
5/5 [==============================] - 0s 27ms/step - loss: 0.3791 - accuracy: 0.0000e+00 - val_loss: 0.5126 - val_accuracy: 0.0000e+00
Epoch 221/500
5/5 [==============================] - 0s 11ms/step - loss: 0.3758 - accuracy: 0.0000e+00 - val_loss: 0.5123 - val_accuracy: 0.0000e+00
Epoch 222/500
5/5 [==============================] - 0s 11ms/step - loss: 0.3773 - accuracy: 0.0000e+00 - val_loss: 0.5138 - val_accuracy: 0.0000e+00
Epoch 223/500
5/5 [==============================] - 0s 11ms/step - loss: 0.3761 - accuracy: 0.0000e+00 - val_loss: 0.5123 - val_accuracy: 0.0000e+00
Epoch 224/500
5/5 [==============================] - 0s 12ms/step - loss: 0.3754 - accuracy: 0.0000e+00 - val_loss: 0.5133 - val_accuracy: 0.0000e+00
Epoch 225/500
5/5 [==============================] - 0s 11ms/step - loss: 0.3736 - accuracy: 0.0000e+00 - val_loss: 0.5121 - val_accuracy: 0.0000e+00
Epoch 226/500
5/5 [==============================] - 0s 10ms/step - loss: 0.3753 - accuracy: 0.0000e+00 - val_loss: 0.5171 - val_accuracy: 0.0000e+00
Epoch 227/500
5/5 [==============================] - 0s 11ms/step - loss: 0.3779 - accuracy: 0.0000e+00 - val_loss: 0.5155 - val_accuracy: 0.0000e+00
Epoch 228/500
5/5 [==============================] - 0s 10ms/step - loss: 0.3784 - accuracy: 0.0000e+00 - val_loss: 0.5109 - val_accuracy: 0.0000e+00
Epoch 229/500
5/5 [==============================] - 0s 10ms/step - loss: 0.3713 - accuracy: 0.0000e+00 - val_loss: 0.5239 - val_accuracy: 0.0000e+00
Epoch 230/500
5/5 [==============================] - 0s 12ms/step - loss: 0.3772 - accuracy: 0.0000e+00 - val_loss: 0.5099 - val_accuracy: 0.0000e+00
Epoch 231/500
5/5 [==============================] - 0s 10ms/step - loss: 0.3764 - accuracy: 0.0000e+00 - val_loss: 0.5106 - val_accuracy: 0.0000e+00
Epoch 232/500
5/5 [==============================] - 0s 10ms/step - loss: 0.3727 - accuracy: 0.0000e+00 - val_loss: 0.5179 - val_accuracy: 0.0000e+00
Epoch 233/500
5/5 [==============================] - 0s 10ms/step - loss: 0.3704 - accuracy: 0.0000e+00 - val_loss: 0.5090 - val_accuracy: 0.0000e+00
Epoch 234/500
5/5 [==============================] - 0s 11ms/step - loss: 0.3732 - accuracy: 0.0000e+00 - val_loss: 0.5094 - val_accuracy: 0.0000e+00
Epoch 235/500
5/5 [==============================] - 0s 27ms/step - loss: 0.3703 - accuracy: 0.0000e+00 - val_loss: 0.5104 - val_accuracy: 0.0000e+00
Epoch 236/500
5/5 [==============================] - 0s 32ms/step - loss: 0.3701 - accuracy: 0.0000e+00 - val_loss: 0.5107 - val_accuracy: 0.0000e+00
Epoch 237/500
5/5 [==============================] - 0s 14ms/step - loss: 0.3695 - accuracy: 0.0000e+00 - val_loss: 0.5082 - val_accuracy: 0.0000e+00
Epoch 238/500
5/5 [==============================] - 0s 11ms/step - loss: 0.3701 - accuracy: 0.0000e+00 - val_loss: 0.5101 - val_accuracy: 0.0000e+00
Epoch 239/500
5/5 [==============================] - 0s 11ms/step - loss: 0.3686 - accuracy: 0.0000e+00 - val_loss: 0.5068 - val_accuracy: 0.0000e+00
Epoch 240/500
5/5 [==============================] - 0s 11ms/step - loss: 0.3684 - accuracy: 0.0000e+00 - val_loss: 0.5122 - val_accuracy: 0.0000e+00
Epoch 241/500
5/5 [==============================] - 0s 11ms/step - loss: 0.3691 - accuracy: 0.0000e+00 - val_loss: 0.5073 - val_accuracy: 0.0000e+00
Epoch 242/500
5/5 [==============================] - 0s 10ms/step - loss: 0.3678 - accuracy: 0.0000e+00 - val_loss: 0.5041 - val_accuracy: 0.0000e+00
Epoch 243/500
5/5 [==============================] - 0s 11ms/step - loss: 0.3653 - accuracy: 0.0000e+00 - val_loss: 0.5054 - val_accuracy: 0.0000e+00
Epoch 244/500
5/5 [==============================] - 0s 25ms/step - loss: 0.3697 - accuracy: 0.0000e+00 - val_loss: 0.5043 - val_accuracy: 0.0000e+00
Epoch 245/500
5/5 [==============================] - 0s 26ms/step - loss: 0.3692 - accuracy: 0.0000e+00 - val_loss: 0.5077 - val_accuracy: 0.0000e+00
Epoch 246/500
5/5 [==============================] - 0s 28ms/step - loss: 0.3656 - accuracy: 0.0000e+00 - val_loss: 0.5058 - val_accuracy: 0.0000e+00
Epoch 247/500
5/5 [==============================] - 0s 29ms/step - loss: 0.3681 - accuracy: 0.0000e+00 - val_loss: 0.5086 - val_accuracy: 0.0000e+00
Epoch 248/500
5/5 [==============================] - 0s 29ms/step - loss: 0.3681 - accuracy: 0.0000e+00 - val_loss: 0.5028 - val_accuracy: 0.0000e+00
Epoch 249/500
5/5 [==============================] - 0s 26ms/step - loss: 0.3643 - accuracy: 0.0000e+00 - val_loss: 0.4997 - val_accuracy: 0.0000e+00
Epoch 250/500
5/5 [==============================] - 0s 14ms/step - loss: 0.3656 - accuracy: 0.0000e+00 - val_loss: 0.5069 - val_accuracy: 0.0000e+00
Epoch 251/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3694 - accuracy: 0.0000e+00 - val_loss: 0.5063 - val_accuracy: 0.0000e+00
Epoch 252/500
5/5 [==============================] - 0s 28ms/step - loss: 0.3630 - accuracy: 0.0000e+00 - val_loss: 0.5034 - val_accuracy: 0.0000e+00
Epoch 253/500
5/5 [==============================] - 0s 28ms/step - loss: 0.3616 - accuracy: 0.0000e+00 - val_loss: 0.5050 - val_accuracy: 0.0000e+00
Epoch 254/500
5/5 [==============================] - 0s 27ms/step - loss: 0.3611 - accuracy: 0.0000e+00 - val_loss: 0.5024 - val_accuracy: 0.0000e+00
Epoch 255/500
5/5 [==============================] - 0s 27ms/step - loss: 0.3606 - accuracy: 0.0000e+00 - val_loss: 0.5023 - val_accuracy: 0.0000e+00
Epoch 256/500
5/5 [==============================] - 0s 24ms/step - loss: 0.3609 - accuracy: 0.0000e+00 - val_loss: 0.5009 - val_accuracy: 0.0000e+00
Epoch 257/500
5/5 [==============================] - 0s 25ms/step - loss: 0.3604 - accuracy: 0.0000e+00 - val_loss: 0.5004 - val_accuracy: 0.0000e+00
Epoch 258/500
5/5 [==============================] - 0s 26ms/step - loss: 0.3606 - accuracy: 0.0000e+00 - val_loss: 0.5035 - val_accuracy: 0.0000e+00
Epoch 259/500
5/5 [==============================] - 0s 12ms/step - loss: 0.3600 - accuracy: 0.0000e+00 - val_loss: 0.5035 - val_accuracy: 0.0000e+00
Epoch 260/500
5/5 [==============================] - 0s 10ms/step - loss: 0.3614 - accuracy: 0.0000e+00 - val_loss: 0.5026 - val_accuracy: 0.0000e+00
Epoch 261/500
5/5 [==============================] - 0s 12ms/step - loss: 0.3588 - accuracy: 0.0000e+00 - val_loss: 0.5022 - val_accuracy: 0.0000e+00
Epoch 262/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3586 - accuracy: 0.0000e+00 - val_loss: 0.5007 - val_accuracy: 0.0000e+00
Epoch 263/500
5/5 [==============================] - 0s 16ms/step - loss: 0.3585 - accuracy: 0.0000e+00 - val_loss: 0.4964 - val_accuracy: 0.0000e+00
Epoch 264/500
5/5 [==============================] - 0s 16ms/step - loss: 0.3579 - accuracy: 0.0000e+00 - val_loss: 0.4962 - val_accuracy: 0.0000e+00
Epoch 265/500
5/5 [==============================] - 0s 18ms/step - loss: 0.3561 - accuracy: 0.0000e+00 - val_loss: 0.4997 - val_accuracy: 0.0000e+00
Epoch 266/500
5/5 [==============================] - 0s 17ms/step - loss: 0.3555 - accuracy: 0.0000e+00 - val_loss: 0.4977 - val_accuracy: 0.0000e+00
Epoch 267/500
5/5 [==============================] - 0s 19ms/step - loss: 0.3563 - accuracy: 0.0000e+00 - val_loss: 0.4976 - val_accuracy: 0.0000e+00
Epoch 268/500
5/5 [==============================] - 0s 16ms/step - loss: 0.3560 - accuracy: 0.0000e+00 - val_loss: 0.4978 - val_accuracy: 0.0000e+00
Epoch 269/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3576 - accuracy: 0.0000e+00 - val_loss: 0.4971 - val_accuracy: 0.0000e+00
Epoch 270/500
5/5 [==============================] - 0s 27ms/step - loss: 0.3594 - accuracy: 0.0000e+00 - val_loss: 0.5009 - val_accuracy: 0.0000e+00
Epoch 271/500
5/5 [==============================] - 0s 31ms/step - loss: 0.3578 - accuracy: 0.0000e+00 - val_loss: 0.4962 - val_accuracy: 0.0000e+00
Epoch 272/500
5/5 [==============================] - 0s 12ms/step - loss: 0.3539 - accuracy: 0.0000e+00 - val_loss: 0.5025 - val_accuracy: 0.0000e+00
Epoch 273/500
5/5 [==============================] - 0s 12ms/step - loss: 0.3550 - accuracy: 0.0000e+00 - val_loss: 0.4945 - val_accuracy: 0.0000e+00
Epoch 274/500
5/5 [==============================] - 0s 12ms/step - loss: 0.3622 - accuracy: 0.0000e+00 - val_loss: 0.4947 - val_accuracy: 0.0000e+00
Epoch 275/500
5/5 [==============================] - 0s 13ms/step - loss: 0.3543 - accuracy: 0.0000e+00 - val_loss: 0.4997 - val_accuracy: 0.0000e+00
Epoch 276/500
5/5 [==============================] - 0s 14ms/step - loss: 0.3521 - accuracy: 0.0000e+00 - val_loss: 0.4907 - val_accuracy: 0.0000e+00
Epoch 277/500
5/5 [==============================] - 0s 16ms/step - loss: 0.3516 - accuracy: 0.0000e+00 - val_loss: 0.4964 - val_accuracy: 0.0000e+00
Epoch 278/500
5/5 [==============================] - 0s 18ms/step - loss: 0.3548 - accuracy: 0.0000e+00 - val_loss: 0.4905 - val_accuracy: 0.0000e+00
Epoch 279/500
5/5 [==============================] - 0s 20ms/step - loss: 0.3596 - accuracy: 0.0000e+00 - val_loss: 0.4912 - val_accuracy: 0.0000e+00
Epoch 280/500
5/5 [==============================] - 0s 20ms/step - loss: 0.3533 - accuracy: 0.0000e+00 - val_loss: 0.4999 - val_accuracy: 0.0000e+00
Epoch 281/500
5/5 [==============================] - 0s 21ms/step - loss: 0.3564 - accuracy: 0.0000e+00 - val_loss: 0.4878 - val_accuracy: 0.0000e+00
Epoch 282/500
5/5 [==============================] - 0s 21ms/step - loss: 0.3507 - accuracy: 0.0000e+00 - val_loss: 0.4990 - val_accuracy: 0.0000e+00
Epoch 283/500
5/5 [==============================] - 0s 22ms/step - loss: 0.3524 - accuracy: 0.0000e+00 - val_loss: 0.4911 - val_accuracy: 0.0000e+00
Epoch 284/500
5/5 [==============================] - 0s 26ms/step - loss: 0.3533 - accuracy: 0.0000e+00 - val_loss: 0.4975 - val_accuracy: 0.0000e+00
Epoch 285/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3491 - accuracy: 0.0000e+00 - val_loss: 0.4939 - val_accuracy: 0.0000e+00
Epoch 286/500
5/5 [==============================] - 0s 18ms/step - loss: 0.3512 - accuracy: 0.0000e+00 - val_loss: 0.4911 - val_accuracy: 0.0000e+00
Epoch 287/500
5/5 [==============================] - 0s 28ms/step - loss: 0.3488 - accuracy: 0.0000e+00 - val_loss: 0.4942 - val_accuracy: 0.0000e+00
Epoch 288/500
5/5 [==============================] - 0s 31ms/step - loss: 0.3493 - accuracy: 0.0000e+00 - val_loss: 0.4894 - val_accuracy: 0.0000e+00
Epoch 289/500
5/5 [==============================] - 0s 31ms/step - loss: 0.3467 - accuracy: 0.0000e+00 - val_loss: 0.4893 - val_accuracy: 0.0000e+00
Epoch 290/500
5/5 [==============================] - 0s 29ms/step - loss: 0.3460 - accuracy: 0.0000e+00 - val_loss: 0.4870 - val_accuracy: 0.0000e+00
Epoch 291/500
5/5 [==============================] - 0s 29ms/step - loss: 0.3473 - accuracy: 0.0000e+00 - val_loss: 0.4965 - val_accuracy: 0.0000e+00
Epoch 292/500
5/5 [==============================] - 0s 30ms/step - loss: 0.3511 - accuracy: 0.0000e+00 - val_loss: 0.4877 - val_accuracy: 0.0000e+00
Epoch 293/500
5/5 [==============================] - 0s 17ms/step - loss: 0.3481 - accuracy: 0.0000e+00 - val_loss: 0.4875 - val_accuracy: 0.0000e+00
Epoch 294/500
5/5 [==============================] - 0s 14ms/step - loss: 0.3530 - accuracy: 0.0000e+00 - val_loss: 0.4937 - val_accuracy: 0.0000e+00
Epoch 295/500
5/5 [==============================] - 0s 14ms/step - loss: 0.3460 - accuracy: 0.0000e+00 - val_loss: 0.4850 - val_accuracy: 0.0000e+00
Epoch 296/500
5/5 [==============================] - 0s 17ms/step - loss: 0.3496 - accuracy: 0.0000e+00 - val_loss: 0.4898 - val_accuracy: 0.0000e+00
Epoch 297/500
5/5 [==============================] - 0s 29ms/step - loss: 0.3436 - accuracy: 0.0000e+00 - val_loss: 0.4916 - val_accuracy: 0.0000e+00
Epoch 298/500
5/5 [==============================] - 0s 30ms/step - loss: 0.3427 - accuracy: 0.0000e+00 - val_loss: 0.4914 - val_accuracy: 0.0000e+00
Epoch 299/500
5/5 [==============================] - 0s 29ms/step - loss: 0.3434 - accuracy: 0.0000e+00 - val_loss: 0.4839 - val_accuracy: 0.0000e+00
Epoch 300/500
5/5 [==============================] - 0s 37ms/step - loss: 0.3426 - accuracy: 0.0000e+00 - val_loss: 0.4877 - val_accuracy: 0.0000e+00
Epoch 301/500
5/5 [==============================] - 0s 33ms/step - loss: 0.3418 - accuracy: 0.0000e+00 - val_loss: 0.4908 - val_accuracy: 0.0000e+00
Epoch 302/500
5/5 [==============================] - 0s 16ms/step - loss: 0.3412 - accuracy: 0.0000e+00 - val_loss: 0.4841 - val_accuracy: 0.0000e+00
Epoch 303/500
5/5 [==============================] - 0s 13ms/step - loss: 0.3411 - accuracy: 0.0000e+00 - val_loss: 0.4843 - val_accuracy: 0.0000e+00
Epoch 304/500
5/5 [==============================] - 0s 13ms/step - loss: 0.3407 - accuracy: 0.0000e+00 - val_loss: 0.4864 - val_accuracy: 0.0000e+00
Epoch 305/500
5/5 [==============================] - 0s 31ms/step - loss: 0.3388 - accuracy: 0.0000e+00 - val_loss: 0.4869 - val_accuracy: 0.0000e+00
Epoch 306/500
5/5 [==============================] - 0s 30ms/step - loss: 0.3392 - accuracy: 0.0000e+00 - val_loss: 0.4858 - val_accuracy: 0.0000e+00
Epoch 307/500
5/5 [==============================] - 0s 30ms/step - loss: 0.3438 - accuracy: 0.0000e+00 - val_loss: 0.4826 - val_accuracy: 0.0000e+00
Epoch 308/500
5/5 [==============================] - 0s 30ms/step - loss: 0.3402 - accuracy: 0.0000e+00 - val_loss: 0.4842 - val_accuracy: 0.0000e+00
Epoch 309/500
5/5 [==============================] - 0s 31ms/step - loss: 0.3423 - accuracy: 0.0000e+00 - val_loss: 0.4865 - val_accuracy: 0.0000e+00
Epoch 310/500
5/5 [==============================] - 0s 33ms/step - loss: 0.3456 - accuracy: 0.0000e+00 - val_loss: 0.4859 - val_accuracy: 0.0000e+00
Epoch 311/500
5/5 [==============================] - 0s 30ms/step - loss: 0.3397 - accuracy: 0.0000e+00 - val_loss: 0.4857 - val_accuracy: 0.0000e+00
Epoch 312/500
5/5 [==============================] - 0s 30ms/step - loss: 0.3400 - accuracy: 0.0000e+00 - val_loss: 0.4810 - val_accuracy: 0.0000e+00
Epoch 313/500
5/5 [==============================] - 0s 32ms/step - loss: 0.3360 - accuracy: 0.0000e+00 - val_loss: 0.4918 - val_accuracy: 0.0000e+00
Epoch 314/500
5/5 [==============================] - 0s 29ms/step - loss: 0.3374 - accuracy: 0.0000e+00 - val_loss: 0.4797 - val_accuracy: 0.0000e+00
Epoch 315/500
5/5 [==============================] - 0s 30ms/step - loss: 0.3344 - accuracy: 0.0000e+00 - val_loss: 0.4871 - val_accuracy: 0.0000e+00
Epoch 316/500
5/5 [==============================] - 0s 30ms/step - loss: 0.3345 - accuracy: 0.0000e+00 - val_loss: 0.4814 - val_accuracy: 0.0000e+00
Epoch 317/500
5/5 [==============================] - 0s 32ms/step - loss: 0.3346 - accuracy: 0.0000e+00 - val_loss: 0.4825 - val_accuracy: 0.0000e+00
Epoch 318/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3337 - accuracy: 0.0000e+00 - val_loss: 0.4824 - val_accuracy: 0.0000e+00
Epoch 319/500
5/5 [==============================] - 0s 11ms/step - loss: 0.3376 - accuracy: 0.0000e+00 - val_loss: 0.4920 - val_accuracy: 0.0000e+00
Epoch 320/500
5/5 [==============================] - 0s 12ms/step - loss: 0.3464 - accuracy: 0.0000e+00 - val_loss: 0.4844 - val_accuracy: 0.0000e+00
Epoch 321/500
5/5 [==============================] - 0s 12ms/step - loss: 0.3410 - accuracy: 0.0000e+00 - val_loss: 0.4848 - val_accuracy: 0.0000e+00
Epoch 322/500
5/5 [==============================] - 0s 17ms/step - loss: 0.3399 - accuracy: 0.0000e+00 - val_loss: 0.4901 - val_accuracy: 0.0000e+00
Epoch 323/500
5/5 [==============================] - 0s 16ms/step - loss: 0.3334 - accuracy: 0.0000e+00 - val_loss: 0.4776 - val_accuracy: 0.0000e+00
Epoch 324/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3327 - accuracy: 0.0000e+00 - val_loss: 0.4848 - val_accuracy: 0.0000e+00
Epoch 325/500
5/5 [==============================] - 0s 31ms/step - loss: 0.3333 - accuracy: 0.0000e+00 - val_loss: 0.4886 - val_accuracy: 0.0000e+00
Epoch 326/500
5/5 [==============================] - 0s 32ms/step - loss: 0.3299 - accuracy: 0.0000e+00 - val_loss: 0.4857 - val_accuracy: 0.0000e+00
Epoch 327/500
5/5 [==============================] - 0s 33ms/step - loss: 0.3331 - accuracy: 0.0000e+00 - val_loss: 0.4813 - val_accuracy: 0.0000e+00
Epoch 328/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3317 - accuracy: 0.0000e+00 - val_loss: 0.4884 - val_accuracy: 0.0000e+00
Epoch 329/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3280 - accuracy: 0.0000e+00 - val_loss: 0.4799 - val_accuracy: 0.0000e+00
Epoch 330/500
5/5 [==============================] - 0s 14ms/step - loss: 0.3278 - accuracy: 0.0000e+00 - val_loss: 0.4856 - val_accuracy: 0.0000e+00
Epoch 331/500
5/5 [==============================] - 0s 14ms/step - loss: 0.3268 - accuracy: 0.0000e+00 - val_loss: 0.4809 - val_accuracy: 0.0000e+00
Epoch 332/500
5/5 [==============================] - 0s 19ms/step - loss: 0.3292 - accuracy: 0.0000e+00 - val_loss: 0.4853 - val_accuracy: 0.0000e+00
Epoch 333/500
5/5 [==============================] - 0s 27ms/step - loss: 0.3275 - accuracy: 0.0000e+00 - val_loss: 0.4812 - val_accuracy: 0.0000e+00
Epoch 334/500
5/5 [==============================] - 0s 28ms/step - loss: 0.3263 - accuracy: 0.0000e+00 - val_loss: 0.4757 - val_accuracy: 0.0000e+00
Epoch 335/500
5/5 [==============================] - 0s 21ms/step - loss: 0.3283 - accuracy: 0.0000e+00 - val_loss: 0.4803 - val_accuracy: 0.0000e+00
Epoch 336/500
5/5 [==============================] - 0s 16ms/step - loss: 0.3277 - accuracy: 0.0000e+00 - val_loss: 0.4806 - val_accuracy: 0.0000e+00
Epoch 337/500
5/5 [==============================] - 0s 17ms/step - loss: 0.3236 - accuracy: 0.0000e+00 - val_loss: 0.4871 - val_accuracy: 0.0000e+00
Epoch 338/500
5/5 [==============================] - 0s 16ms/step - loss: 0.3273 - accuracy: 0.0000e+00 - val_loss: 0.4868 - val_accuracy: 0.0000e+00
Epoch 339/500
5/5 [==============================] - 0s 16ms/step - loss: 0.3251 - accuracy: 0.0000e+00 - val_loss: 0.4854 - val_accuracy: 0.0000e+00
Epoch 340/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3239 - accuracy: 0.0000e+00 - val_loss: 0.4865 - val_accuracy: 0.0000e+00
Epoch 341/500
5/5 [==============================] - 0s 23ms/step - loss: 0.3255 - accuracy: 0.0000e+00 - val_loss: 0.4872 - val_accuracy: 0.0000e+00
Epoch 342/500
5/5 [==============================] - 0s 32ms/step - loss: 0.3219 - accuracy: 0.0000e+00 - val_loss: 0.4804 - val_accuracy: 0.0000e+00
Epoch 343/500
5/5 [==============================] - 0s 29ms/step - loss: 0.3254 - accuracy: 0.0000e+00 - val_loss: 0.4847 - val_accuracy: 0.0000e+00
Epoch 344/500
5/5 [==============================] - 0s 30ms/step - loss: 0.3253 - accuracy: 0.0000e+00 - val_loss: 0.4806 - val_accuracy: 0.0000e+00
Epoch 345/500
5/5 [==============================] - 0s 27ms/step - loss: 0.3246 - accuracy: 0.0000e+00 - val_loss: 0.4837 - val_accuracy: 0.0000e+00
Epoch 346/500
5/5 [==============================] - 0s 31ms/step - loss: 0.3236 - accuracy: 0.0000e+00 - val_loss: 0.4844 - val_accuracy: 0.0000e+00
Epoch 347/500
5/5 [==============================] - 0s 30ms/step - loss: 0.3196 - accuracy: 0.0000e+00 - val_loss: 0.4823 - val_accuracy: 0.0000e+00
Epoch 348/500
5/5 [==============================] - 0s 28ms/step - loss: 0.3211 - accuracy: 0.0000e+00 - val_loss: 0.4878 - val_accuracy: 0.0000e+00
Epoch 349/500
5/5 [==============================] - 0s 16ms/step - loss: 0.3218 - accuracy: 0.0000e+00 - val_loss: 0.4796 - val_accuracy: 0.0000e+00
Epoch 350/500
5/5 [==============================] - 0s 12ms/step - loss: 0.3217 - accuracy: 0.0000e+00 - val_loss: 0.4834 - val_accuracy: 0.0000e+00
Epoch 351/500
5/5 [==============================] - 0s 11ms/step - loss: 0.3195 - accuracy: 0.0000e+00 - val_loss: 0.4865 - val_accuracy: 0.0000e+00
Epoch 352/500
5/5 [==============================] - 0s 12ms/step - loss: 0.3185 - accuracy: 0.0000e+00 - val_loss: 0.4806 - val_accuracy: 0.0000e+00
Epoch 353/500
5/5 [==============================] - 0s 10ms/step - loss: 0.3184 - accuracy: 0.0000e+00 - val_loss: 0.4796 - val_accuracy: 0.0000e+00
Epoch 354/500
5/5 [==============================] - 0s 10ms/step - loss: 0.3167 - accuracy: 0.0000e+00 - val_loss: 0.4856 - val_accuracy: 0.0000e+00
Epoch 355/500
5/5 [==============================] - 0s 11ms/step - loss: 0.3227 - accuracy: 0.0000e+00 - val_loss: 0.4853 - val_accuracy: 0.0000e+00
Epoch 356/500
5/5 [==============================] - 0s 14ms/step - loss: 0.3185 - accuracy: 0.0000e+00 - val_loss: 0.4801 - val_accuracy: 0.0000e+00
Epoch 357/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3224 - accuracy: 0.0000e+00 - val_loss: 0.4882 - val_accuracy: 0.0000e+00
Epoch 358/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3187 - accuracy: 0.0000e+00 - val_loss: 0.4829 - val_accuracy: 0.0000e+00
Epoch 359/500
5/5 [==============================] - 0s 16ms/step - loss: 0.3156 - accuracy: 0.0000e+00 - val_loss: 0.4846 - val_accuracy: 0.0000e+00
Epoch 360/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3173 - accuracy: 0.0000e+00 - val_loss: 0.4836 - val_accuracy: 0.0000e+00
Epoch 361/500
5/5 [==============================] - 0s 19ms/step - loss: 0.3165 - accuracy: 0.0000e+00 - val_loss: 0.4853 - val_accuracy: 0.0000e+00
Epoch 362/500
5/5 [==============================] - 0s 23ms/step - loss: 0.3206 - accuracy: 0.0000e+00 - val_loss: 0.4789 - val_accuracy: 0.0000e+00
Epoch 363/500
5/5 [==============================] - 0s 17ms/step - loss: 0.3328 - accuracy: 0.0000e+00 - val_loss: 0.4811 - val_accuracy: 0.0000e+00
Epoch 364/500
5/5 [==============================] - 0s 12ms/step - loss: 0.3210 - accuracy: 0.0000e+00 - val_loss: 0.4877 - val_accuracy: 0.0000e+00
Epoch 365/500
5/5 [==============================] - 0s 13ms/step - loss: 0.3159 - accuracy: 0.0000e+00 - val_loss: 0.4828 - val_accuracy: 0.0000e+00
Epoch 366/500
5/5 [==============================] - 0s 10ms/step - loss: 0.3192 - accuracy: 0.0000e+00 - val_loss: 0.4786 - val_accuracy: 0.0000e+00
Epoch 367/500
5/5 [==============================] - 0s 11ms/step - loss: 0.3160 - accuracy: 0.0000e+00 - val_loss: 0.4853 - val_accuracy: 0.0000e+00
Epoch 368/500
5/5 [==============================] - 0s 14ms/step - loss: 0.3153 - accuracy: 0.0000e+00 - val_loss: 0.4840 - val_accuracy: 0.0000e+00
Epoch 369/500
5/5 [==============================] - 0s 14ms/step - loss: 0.3198 - accuracy: 0.0000e+00 - val_loss: 0.4800 - val_accuracy: 0.0000e+00
Epoch 370/500
5/5 [==============================] - 0s 14ms/step - loss: 0.3148 - accuracy: 0.0000e+00 - val_loss: 0.4904 - val_accuracy: 0.0000e+00
Epoch 371/500
5/5 [==============================] - 0s 11ms/step - loss: 0.3151 - accuracy: 0.0000e+00 - val_loss: 0.4893 - val_accuracy: 0.0000e+00
Epoch 372/500
5/5 [==============================] - 0s 11ms/step - loss: 0.3135 - accuracy: 0.0000e+00 - val_loss: 0.4837 - val_accuracy: 0.0000e+00
Epoch 373/500
5/5 [==============================] - 0s 13ms/step - loss: 0.3131 - accuracy: 0.0000e+00 - val_loss: 0.4870 - val_accuracy: 0.0000e+00
Epoch 374/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3188 - accuracy: 0.0000e+00 - val_loss: 0.4815 - val_accuracy: 0.0000e+00
Epoch 375/500
5/5 [==============================] - 0s 30ms/step - loss: 0.3183 - accuracy: 0.0000e+00 - val_loss: 0.4936 - val_accuracy: 0.0000e+00
Epoch 376/500
5/5 [==============================] - 0s 30ms/step - loss: 0.3126 - accuracy: 0.0000e+00 - val_loss: 0.4834 - val_accuracy: 0.0000e+00
Epoch 377/500
5/5 [==============================] - 0s 31ms/step - loss: 0.3094 - accuracy: 0.0000e+00 - val_loss: 0.4805 - val_accuracy: 0.0000e+00
Epoch 378/500
5/5 [==============================] - 0s 13ms/step - loss: 0.3091 - accuracy: 0.0000e+00 - val_loss: 0.4856 - val_accuracy: 0.0000e+00
Epoch 379/500
5/5 [==============================] - 0s 11ms/step - loss: 0.3077 - accuracy: 0.0000e+00 - val_loss: 0.4839 - val_accuracy: 0.0000e+00
Epoch 380/500
5/5 [==============================] - 0s 12ms/step - loss: 0.3098 - accuracy: 0.0000e+00 - val_loss: 0.4858 - val_accuracy: 0.0000e+00
Epoch 381/500
5/5 [==============================] - 0s 31ms/step - loss: 0.3088 - accuracy: 0.0000e+00 - val_loss: 0.4852 - val_accuracy: 0.0000e+00
Epoch 382/500
5/5 [==============================] - 0s 20ms/step - loss: 0.3059 - accuracy: 0.0000e+00 - val_loss: 0.4802 - val_accuracy: 0.0000e+00
Epoch 383/500
5/5 [==============================] - 0s 12ms/step - loss: 0.3074 - accuracy: 0.0000e+00 - val_loss: 0.4818 - val_accuracy: 0.0000e+00
Epoch 384/500
5/5 [==============================] - 0s 12ms/step - loss: 0.3080 - accuracy: 0.0000e+00 - val_loss: 0.4869 - val_accuracy: 0.0000e+00
Epoch 385/500
5/5 [==============================] - 0s 15ms/step - loss: 0.3129 - accuracy: 0.0000e+00 - val_loss: 0.4865 - val_accuracy: 0.0000e+00
Epoch 386/500
5/5 [==============================] - 0s 17ms/step - loss: 0.3118 - accuracy: 0.0000e+00 - val_loss: 0.4832 - val_accuracy: 0.0000e+00
Epoch 387/500
5/5 [==============================] - 0s 18ms/step - loss: 0.3108 - accuracy: 0.0000e+00 - val_loss: 0.4846 - val_accuracy: 0.0000e+00
Epoch 388/500
5/5 [==============================] - 0s 23ms/step - loss: 0.3142 - accuracy: 0.0000e+00 - val_loss: 0.4970 - val_accuracy: 0.0000e+00
Epoch 389/500
5/5 [==============================] - 0s 22ms/step - loss: 0.3114 - accuracy: 0.0000e+00 - val_loss: 0.4811 - val_accuracy: 0.0000e+00
Epoch 390/500
5/5 [==============================] - 0s 21ms/step - loss: 0.3051 - accuracy: 0.0000e+00 - val_loss: 0.4837 - val_accuracy: 0.0000e+00
Epoch 391/500
5/5 [==============================] - 0s 22ms/step - loss: 0.3065 - accuracy: 0.0000e+00 - val_loss: 0.4871 - val_accuracy: 0.0000e+00
Epoch 392/500
5/5 [==============================] - 0s 22ms/step - loss: 0.3057 - accuracy: 0.0000e+00 - val_loss: 0.4822 - val_accuracy: 0.0000e+00
Epoch 393/500
5/5 [==============================] - 0s 23ms/step - loss: 0.3041 - accuracy: 0.0000e+00 - val_loss: 0.4845 - val_accuracy: 0.0000e+00
Epoch 394/500
5/5 [==============================] - 0s 22ms/step - loss: 0.3072 - accuracy: 0.0000e+00 - val_loss: 0.4837 - val_accuracy: 0.0000e+00
Epoch 395/500
5/5 [==============================] - 0s 21ms/step - loss: 0.3115 - accuracy: 0.0000e+00 - val_loss: 0.4882 - val_accuracy: 0.0000e+00
Epoch 396/500
5/5 [==============================] - 0s 27ms/step - loss: 0.3047 - accuracy: 0.0000e+00 - val_loss: 0.4859 - val_accuracy: 0.0000e+00
Epoch 397/500
5/5 [==============================] - 0s 28ms/step - loss: 0.3053 - accuracy: 0.0000e+00 - val_loss: 0.4855 - val_accuracy: 0.0000e+00
Epoch 398/500
5/5 [==============================] - 0s 26ms/step - loss: 0.3091 - accuracy: 0.0000e+00 - val_loss: 0.4802 - val_accuracy: 0.0000e+00
Epoch 399/500
5/5 [==============================] - 0s 27ms/step - loss: 0.3039 - accuracy: 0.0000e+00 - val_loss: 0.4845 - val_accuracy: 0.0000e+00
Epoch 400/500
5/5 [==============================] - 0s 24ms/step - loss: 0.3011 - accuracy: 0.0000e+00 - val_loss: 0.4893 - val_accuracy: 0.0000e+00
Epoch 401/500
5/5 [==============================] - 0s 14ms/step - loss: 0.2998 - accuracy: 0.0000e+00 - val_loss: 0.4889 - val_accuracy: 0.0000e+00
Epoch 402/500
5/5 [==============================] - 0s 14ms/step - loss: 0.2997 - accuracy: 0.0000e+00 - val_loss: 0.4877 - val_accuracy: 0.0000e+00
Epoch 403/500
5/5 [==============================] - 0s 14ms/step - loss: 0.3004 - accuracy: 0.0000e+00 - val_loss: 0.4888 - val_accuracy: 0.0000e+00
Epoch 404/500
5/5 [==============================] - 0s 17ms/step - loss: 0.3004 - accuracy: 0.0000e+00 - val_loss: 0.4856 - val_accuracy: 0.0000e+00
Epoch 405/500
5/5 [==============================] - 0s 33ms/step - loss: 0.2985 - accuracy: 0.0000e+00 - val_loss: 0.4869 - val_accuracy: 0.0000e+00
Epoch 406/500
5/5 [==============================] - 0s 30ms/step - loss: 0.2999 - accuracy: 0.0000e+00 - val_loss: 0.4909 - val_accuracy: 0.0000e+00
Epoch 407/500
5/5 [==============================] - 0s 29ms/step - loss: 0.3005 - accuracy: 0.0000e+00 - val_loss: 0.4883 - val_accuracy: 0.0000e+00
Epoch 408/500
5/5 [==============================] - 0s 28ms/step - loss: 0.3021 - accuracy: 0.0000e+00 - val_loss: 0.4885 - val_accuracy: 0.0000e+00
Epoch 409/500
5/5 [==============================] - 0s 24ms/step - loss: 0.3046 - accuracy: 0.0000e+00 - val_loss: 0.4922 - val_accuracy: 0.0000e+00
Epoch 410/500
5/5 [==============================] - 0s 18ms/step - loss: 0.2986 - accuracy: 0.0000e+00 - val_loss: 0.4864 - val_accuracy: 0.0000e+00
Epoch 411/500
5/5 [==============================] - 0s 18ms/step - loss: 0.3009 - accuracy: 0.0000e+00 - val_loss: 0.4959 - val_accuracy: 0.0000e+00
Epoch 412/500
5/5 [==============================] - 0s 27ms/step - loss: 0.2991 - accuracy: 0.0000e+00 - val_loss: 0.4862 - val_accuracy: 0.0000e+00
Epoch 413/500
5/5 [==============================] - 0s 27ms/step - loss: 0.2966 - accuracy: 0.0000e+00 - val_loss: 0.4837 - val_accuracy: 0.0000e+00
Epoch 414/500
5/5 [==============================] - 0s 27ms/step - loss: 0.2959 - accuracy: 0.0000e+00 - val_loss: 0.4896 - val_accuracy: 0.0000e+00
Epoch 415/500
5/5 [==============================] - 0s 25ms/step - loss: 0.3033 - accuracy: 0.0000e+00 - val_loss: 0.4919 - val_accuracy: 0.0000e+00
Epoch 416/500
5/5 [==============================] - 0s 27ms/step - loss: 0.3025 - accuracy: 0.0000e+00 - val_loss: 0.4947 - val_accuracy: 0.0000e+00
Epoch 417/500
5/5 [==============================] - 0s 28ms/step - loss: 0.2989 - accuracy: 0.0000e+00 - val_loss: 0.4864 - val_accuracy: 0.0000e+00
Epoch 418/500
5/5 [==============================] - 0s 27ms/step - loss: 0.2949 - accuracy: 0.0000e+00 - val_loss: 0.4879 - val_accuracy: 0.0000e+00
Epoch 419/500
5/5 [==============================] - 0s 11ms/step - loss: 0.2941 - accuracy: 0.0000e+00 - val_loss: 0.4937 - val_accuracy: 0.0000e+00
Epoch 420/500
5/5 [==============================] - 0s 11ms/step - loss: 0.2947 - accuracy: 0.0000e+00 - val_loss: 0.4936 - val_accuracy: 0.0000e+00
Epoch 421/500
5/5 [==============================] - 0s 11ms/step - loss: 0.2965 - accuracy: 0.0000e+00 - val_loss: 0.4923 - val_accuracy: 0.0000e+00
Epoch 422/500
5/5 [==============================] - 0s 11ms/step - loss: 0.3002 - accuracy: 0.0000e+00 - val_loss: 0.4999 - val_accuracy: 0.0000e+00
Epoch 423/500
5/5 [==============================] - 0s 11ms/step - loss: 0.2934 - accuracy: 0.0000e+00 - val_loss: 0.4899 - val_accuracy: 0.0000e+00
Epoch 424/500
5/5 [==============================] - 0s 16ms/step - loss: 0.2930 - accuracy: 0.0000e+00 - val_loss: 0.4913 - val_accuracy: 0.0000e+00
Epoch 425/500
5/5 [==============================] - 0s 29ms/step - loss: 0.2910 - accuracy: 0.0000e+00 - val_loss: 0.4927 - val_accuracy: 0.0000e+00
Epoch 426/500
5/5 [==============================] - 0s 27ms/step - loss: 0.2945 - accuracy: 0.0000e+00 - val_loss: 0.4928 - val_accuracy: 0.0000e+00
Epoch 427/500
5/5 [==============================] - 0s 28ms/step - loss: 0.3016 - accuracy: 0.0000e+00 - val_loss: 0.4940 - val_accuracy: 0.0000e+00
Epoch 428/500
5/5 [==============================] - 0s 27ms/step - loss: 0.2929 - accuracy: 0.0000e+00 - val_loss: 0.4955 - val_accuracy: 0.0000e+00
Epoch 429/500
5/5 [==============================] - 0s 29ms/step - loss: 0.2928 - accuracy: 0.0000e+00 - val_loss: 0.5054 - val_accuracy: 0.0000e+00
Epoch 430/500
5/5 [==============================] - 0s 29ms/step - loss: 0.2970 - accuracy: 0.0000e+00 - val_loss: 0.4946 - val_accuracy: 0.0000e+00
Epoch 431/500
5/5 [==============================] - 0s 19ms/step - loss: 0.2898 - accuracy: 0.0000e+00 - val_loss: 0.4973 - val_accuracy: 0.0000e+00
Epoch 432/500
5/5 [==============================] - 0s 27ms/step - loss: 0.2982 - accuracy: 0.0000e+00 - val_loss: 0.5003 - val_accuracy: 0.0000e+00
Epoch 433/500
5/5 [==============================] - 0s 31ms/step - loss: 0.3126 - accuracy: 0.0000e+00 - val_loss: 0.5165 - val_accuracy: 0.0000e+00
Epoch 434/500
5/5 [==============================] - 0s 27ms/step - loss: 0.3152 - accuracy: 0.0000e+00 - val_loss: 0.4980 - val_accuracy: 0.0000e+00
Epoch 435/500
5/5 [==============================] - 0s 26ms/step - loss: 0.3021 - accuracy: 0.0000e+00 - val_loss: 0.5228 - val_accuracy: 0.0000e+00
Epoch 436/500
5/5 [==============================] - 0s 27ms/step - loss: 0.3015 - accuracy: 0.0000e+00 - val_loss: 0.4923 - val_accuracy: 0.0000e+00
Epoch 437/500
5/5 [==============================] - 0s 26ms/step - loss: 0.2973 - accuracy: 0.0000e+00 - val_loss: 0.5035 - val_accuracy: 0.0000e+00
Epoch 438/500
5/5 [==============================] - 0s 27ms/step - loss: 0.2900 - accuracy: 0.0000e+00 - val_loss: 0.4941 - val_accuracy: 0.0000e+00
Epoch 439/500
5/5 [==============================] - 0s 15ms/step - loss: 0.2902 - accuracy: 0.0000e+00 - val_loss: 0.5000 - val_accuracy: 0.0000e+00
Epoch 440/500
5/5 [==============================] - 0s 16ms/step - loss: 0.2929 - accuracy: 0.0000e+00 - val_loss: 0.4958 - val_accuracy: 0.0000e+00
Epoch 441/500
5/5 [==============================] - 0s 28ms/step - loss: 0.2931 - accuracy: 0.0000e+00 - val_loss: 0.4902 - val_accuracy: 0.0000e+00
Epoch 442/500
5/5 [==============================] - 0s 30ms/step - loss: 0.2886 - accuracy: 0.0000e+00 - val_loss: 0.4949 - val_accuracy: 0.0000e+00
Epoch 443/500
5/5 [==============================] - 0s 34ms/step - loss: 0.2863 - accuracy: 0.0000e+00 - val_loss: 0.4934 - val_accuracy: 0.0000e+00
Epoch 444/500
5/5 [==============================] - 0s 27ms/step - loss: 0.2887 - accuracy: 0.0000e+00 - val_loss: 0.5004 - val_accuracy: 0.0000e+00
Epoch 445/500
5/5 [==============================] - 0s 27ms/step - loss: 0.2874 - accuracy: 0.0000e+00 - val_loss: 0.4896 - val_accuracy: 0.0000e+00
Epoch 446/500
5/5 [==============================] - 0s 28ms/step - loss: 0.2895 - accuracy: 0.0000e+00 - val_loss: 0.4959 - val_accuracy: 0.0000e+00
Epoch 447/500
5/5 [==============================] - 0s 25ms/step - loss: 0.2847 - accuracy: 0.0000e+00 - val_loss: 0.5031 - val_accuracy: 0.0000e+00
Epoch 448/500
5/5 [==============================] - 0s 11ms/step - loss: 0.2896 - accuracy: 0.0000e+00 - val_loss: 0.4994 - val_accuracy: 0.0000e+00
Epoch 449/500
5/5 [==============================] - 0s 19ms/step - loss: 0.2868 - accuracy: 0.0000e+00 - val_loss: 0.4950 - val_accuracy: 0.0000e+00
Epoch 450/500
5/5 [==============================] - 0s 28ms/step - loss: 0.2895 - accuracy: 0.0000e+00 - val_loss: 0.5008 - val_accuracy: 0.0000e+00
Epoch 451/500
5/5 [==============================] - 0s 33ms/step - loss: 0.2863 - accuracy: 0.0000e+00 - val_loss: 0.4924 - val_accuracy: 0.0000e+00
Epoch 452/500
5/5 [==============================] - 0s 29ms/step - loss: 0.2851 - accuracy: 0.0000e+00 - val_loss: 0.5112 - val_accuracy: 0.0000e+00
Epoch 453/500
5/5 [==============================] - 0s 23ms/step - loss: 0.2848 - accuracy: 0.0000e+00 - val_loss: 0.4964 - val_accuracy: 0.0000e+00
Epoch 454/500
5/5 [==============================] - 0s 12ms/step - loss: 0.2940 - accuracy: 0.0000e+00 - val_loss: 0.5114 - val_accuracy: 0.0000e+00
Epoch 455/500
5/5 [==============================] - 0s 13ms/step - loss: 0.2888 - accuracy: 0.0000e+00 - val_loss: 0.5003 - val_accuracy: 0.0000e+00
Epoch 456/500
5/5 [==============================] - 0s 13ms/step - loss: 0.2857 - accuracy: 0.0000e+00 - val_loss: 0.5069 - val_accuracy: 0.0000e+00
Epoch 457/500
5/5 [==============================] - 0s 15ms/step - loss: 0.2859 - accuracy: 0.0000e+00 - val_loss: 0.4980 - val_accuracy: 0.0000e+00
Epoch 458/500
5/5 [==============================] - 0s 15ms/step - loss: 0.2834 - accuracy: 0.0000e+00 - val_loss: 0.5034 - val_accuracy: 0.0000e+00
Epoch 459/500
5/5 [==============================] - 0s 14ms/step - loss: 0.2848 - accuracy: 0.0000e+00 - val_loss: 0.4985 - val_accuracy: 0.0000e+00
Epoch 460/500
5/5 [==============================] - 0s 16ms/step - loss: 0.2824 - accuracy: 0.0000e+00 - val_loss: 0.4960 - val_accuracy: 0.0000e+00
Epoch 461/500
5/5 [==============================] - 0s 15ms/step - loss: 0.2817 - accuracy: 0.0000e+00 - val_loss: 0.4998 - val_accuracy: 0.0000e+00
Epoch 462/500
5/5 [==============================] - 0s 16ms/step - loss: 0.2832 - accuracy: 0.0000e+00 - val_loss: 0.4989 - val_accuracy: 0.0000e+00
Epoch 463/500
5/5 [==============================] - 0s 21ms/step - loss: 0.2815 - accuracy: 0.0000e+00 - val_loss: 0.4995 - val_accuracy: 0.0000e+00
Epoch 464/500
5/5 [==============================] - 0s 30ms/step - loss: 0.2851 - accuracy: 0.0000e+00 - val_loss: 0.5092 - val_accuracy: 0.0000e+00
Epoch 465/500
5/5 [==============================] - 0s 29ms/step - loss: 0.2858 - accuracy: 0.0000e+00 - val_loss: 0.5026 - val_accuracy: 0.0000e+00
Epoch 466/500
5/5 [==============================] - 0s 26ms/step - loss: 0.2864 - accuracy: 0.0000e+00 - val_loss: 0.5146 - val_accuracy: 0.0000e+00
Epoch 467/500
5/5 [==============================] - 0s 26ms/step - loss: 0.2872 - accuracy: 0.0000e+00 - val_loss: 0.4964 - val_accuracy: 0.0000e+00
Epoch 468/500
5/5 [==============================] - 0s 28ms/step - loss: 0.2833 - accuracy: 0.0000e+00 - val_loss: 0.5101 - val_accuracy: 0.0000e+00
Epoch 469/500
5/5 [==============================] - 0s 16ms/step - loss: 0.2805 - accuracy: 0.0000e+00 - val_loss: 0.4959 - val_accuracy: 0.0000e+00
Epoch 470/500
5/5 [==============================] - 0s 11ms/step - loss: 0.2838 - accuracy: 0.0000e+00 - val_loss: 0.5073 - val_accuracy: 0.0000e+00
Epoch 471/500
5/5 [==============================] - 0s 14ms/step - loss: 0.2807 - accuracy: 0.0000e+00 - val_loss: 0.5005 - val_accuracy: 0.0000e+00
Epoch 472/500
5/5 [==============================] - 0s 32ms/step - loss: 0.2869 - accuracy: 0.0000e+00 - val_loss: 0.5083 - val_accuracy: 0.0000e+00
Epoch 473/500
5/5 [==============================] - 0s 35ms/step - loss: 0.2835 - accuracy: 0.0000e+00 - val_loss: 0.5015 - val_accuracy: 0.0000e+00
Epoch 474/500
5/5 [==============================] - 0s 30ms/step - loss: 0.2768 - accuracy: 0.0000e+00 - val_loss: 0.5079 - val_accuracy: 0.0000e+00
Epoch 475/500
5/5 [==============================] - 0s 26ms/step - loss: 0.2809 - accuracy: 0.0000e+00 - val_loss: 0.5008 - val_accuracy: 0.0000e+00
Epoch 476/500
5/5 [==============================] - 0s 31ms/step - loss: 0.2819 - accuracy: 0.0000e+00 - val_loss: 0.5015 - val_accuracy: 0.0000e+00
Epoch 477/500
5/5 [==============================] - 0s 29ms/step - loss: 0.2858 - accuracy: 0.0000e+00 - val_loss: 0.5046 - val_accuracy: 0.0000e+00
Epoch 478/500
5/5 [==============================] - 0s 15ms/step - loss: 0.2765 - accuracy: 0.0000e+00 - val_loss: 0.5050 - val_accuracy: 0.0000e+00
Epoch 479/500
5/5 [==============================] - 0s 13ms/step - loss: 0.2778 - accuracy: 0.0000e+00 - val_loss: 0.5083 - val_accuracy: 0.0000e+00
Epoch 480/500
5/5 [==============================] - 0s 14ms/step - loss: 0.2762 - accuracy: 0.0000e+00 - val_loss: 0.5005 - val_accuracy: 0.0000e+00
Epoch 481/500
5/5 [==============================] - 0s 11ms/step - loss: 0.2750 - accuracy: 0.0000e+00 - val_loss: 0.5049 - val_accuracy: 0.0000e+00
Epoch 482/500
5/5 [==============================] - 0s 11ms/step - loss: 0.2775 - accuracy: 0.0000e+00 - val_loss: 0.5060 - val_accuracy: 0.0000e+00
Epoch 483/500
5/5 [==============================] - 0s 12ms/step - loss: 0.2775 - accuracy: 0.0000e+00 - val_loss: 0.4984 - val_accuracy: 0.0000e+00
Epoch 484/500
5/5 [==============================] - 0s 12ms/step - loss: 0.2753 - accuracy: 0.0000e+00 - val_loss: 0.5091 - val_accuracy: 0.0000e+00
Epoch 485/500
5/5 [==============================] - 0s 14ms/step - loss: 0.2837 - accuracy: 0.0000e+00 - val_loss: 0.5088 - val_accuracy: 0.0000e+00
Epoch 486/500
5/5 [==============================] - 0s 13ms/step - loss: 0.2786 - accuracy: 0.0000e+00 - val_loss: 0.5020 - val_accuracy: 0.0000e+00
Epoch 487/500
5/5 [==============================] - 0s 13ms/step - loss: 0.2804 - accuracy: 0.0000e+00 - val_loss: 0.5278 - val_accuracy: 0.0000e+00
Epoch 488/500
5/5 [==============================] - 0s 13ms/step - loss: 0.2843 - accuracy: 0.0000e+00 - val_loss: 0.5141 - val_accuracy: 0.0000e+00
Epoch 489/500
5/5 [==============================] - 0s 11ms/step - loss: 0.2851 - accuracy: 0.0000e+00 - val_loss: 0.5204 - val_accuracy: 0.0000e+00
Epoch 490/500
5/5 [==============================] - 0s 12ms/step - loss: 0.2792 - accuracy: 0.0000e+00 - val_loss: 0.5126 - val_accuracy: 0.0000e+00
Epoch 491/500
5/5 [==============================] - 0s 12ms/step - loss: 0.2793 - accuracy: 0.0000e+00 - val_loss: 0.5149 - val_accuracy: 0.0000e+00
Epoch 492/500
5/5 [==============================] - 0s 12ms/step - loss: 0.2776 - accuracy: 0.0000e+00 - val_loss: 0.5051 - val_accuracy: 0.0000e+00
Epoch 493/500
5/5 [==============================] - 0s 12ms/step - loss: 0.2755 - accuracy: 0.0000e+00 - val_loss: 0.5083 - val_accuracy: 0.0000e+00
Epoch 494/500
5/5 [==============================] - 0s 11ms/step - loss: 0.2758 - accuracy: 0.0000e+00 - val_loss: 0.5115 - val_accuracy: 0.0000e+00
Epoch 495/500
5/5 [==============================] - 0s 13ms/step - loss: 0.2758 - accuracy: 0.0000e+00 - val_loss: 0.5115 - val_accuracy: 0.0000e+00
Epoch 496/500
5/5 [==============================] - 0s 28ms/step - loss: 0.2744 - accuracy: 0.0000e+00 - val_loss: 0.5061 - val_accuracy: 0.0000e+00
Epoch 497/500
5/5 [==============================] - 0s 28ms/step - loss: 0.2807 - accuracy: 0.0000e+00 - val_loss: 0.5228 - val_accuracy: 0.0000e+00
Epoch 498/500
5/5 [==============================] - 0s 27ms/step - loss: 0.2771 - accuracy: 0.0000e+00 - val_loss: 0.5122 - val_accuracy: 0.0000e+00
Epoch 499/500
5/5 [==============================] - 0s 17ms/step - loss: 0.2757 - accuracy: 0.0000e+00 - val_loss: 0.5394 - val_accuracy: 0.0000e+00
Epoch 500/500
5/5 [==============================] - 0s 32ms/step - loss: 0.2842 - accuracy: 0.0000e+00 - val_loss: 0.5024 - val_accuracy: 0.0000e+00

loss_train = Network_Regressor.history['loss']
loss_val = Network_Regressor.history['val_loss']
epochs = range(1,EPOCH+1)
plt.plot(epochs, loss_train, 'g', label='Training loss')
plt.plot(epochs, loss_val, 'b', label='validation loss')
plt.title('Training and Validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()
plt.show()

from tensorflow.keras.models import model_from_json


# Pickle model to JSON
Regressor_model_json = NN_model_Regressor.to_json()
with open("Regressor_model.json", "w") as json_file:
    json_file.write(Regressor_model_json)
# Pickle weights to HDF5
NN_model_Regressor.save_weights("Regressor_model.h5")
print("Saved model to disk")


# load json and create model
json_file = open('Regressor_model.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
loaded_model = model_from_json(loaded_model_json)
# load weights into new model
loaded_model.load_weights("Regressor_model.h5")
print("Loaded model from disk")

# Evaluate
loaded_model.compile(loss='mse', optimizer='adam', metrics=['accuracy'])
score = loaded_model.evaluate(X_Test_S,y_test, verbose=1)
print("%s: %.2f%%" % (loaded_model.metrics_names[1], score[1]*100))

Saved model to disk
Loaded model from disk
15/15 [==============================] - 1s 2ms/step - loss: 0.5024 - accuracy: 0.0000e+00
accuracy: 0.00%

Part 2 - Autonomous Vehicles Project

# Seaborn is based on matplotlib, which aids in drawing attractive and informative statistical graphics.
import seaborn as sns
import tensorflow 
print(tensorflow.__version__)

2.7.0

# suppress display of warnings
warnings.filterwarnings('ignore')

# display all dataframe columns
pd.options.display.max_columns = None

# to set the limit to 3 decimals
pd.options.display.float_format = '{:.7f}'.format

# display all dataframe rows
pd.options.display.max_rows = None

Read Data

import h5py

# Open the file as readonly
h5f = h5py.File('Part - 4 - Autonomous_Vehicles_SVHN_single_grey1.h5', 'r')

h5f.keys()

<KeysViewHDF5 ['X_test', 'X_train', 'X_val', 'y_test', 'y_train', 'y_val']>

Data Analysis and Preparation

# Load the training, test and validation set
X_train = h5f['X_train'][:]
y_train = h5f['y_train'][:]
X_test = h5f['X_test'][:]
y_test = h5f['y_test'][:]

#Let us see the contents of features and labels of one example from the images
X_train[:1] 

array([[[ 33.0704,  30.2601,  26.852 , ...,  71.4471,  58.2204,
          42.9939],
        [ 25.2283,  25.5533,  29.9765, ..., 113.0209, 103.3639,
          84.2949],
        [ 26.2775,  22.6137,  40.4763, ..., 113.3028, 121.775 ,
         115.4228],
        ...,
        [ 28.5502,  36.212 ,  45.0801, ...,  24.1359,  25.0927,
          26.0603],
        [ 38.4352,  26.4733,  23.2717, ...,  28.1094,  29.4683,
          30.0661],
        [ 50.2984,  26.0773,  24.0389, ...,  49.6682,  50.853 ,
          53.0377]]], dtype=float32)

y_train[:1]

array([2], dtype=uint8)

X_test[:1]

array([[[ 40.558 ,  46.7917,  48.9764, ..., 112.1153, 112.9904,
         112.1646],
        [ 39.4379,  44.2911,  47.1768, ..., 111.0122, 110.9475,
         109.9368],
        [ 38.4488,  43.6394,  48.7098, ..., 109.8921, 109.9414,
         109.1048],
        ...,
        [ 34.9869,  35.4707,  39.6676, ..., 109.211 , 109.9074,
         112.7346],
        [ 35.6602,  35.5462,  40.3193, ..., 110.9998, 112.049 ,
         114.3431],
        [ 36.1871,  35.4214,  40.6998, ..., 110.0169, 111.2017,
         114.1906]]], dtype=float32)

y_test[:1]

array([1], dtype=uint8)

Visualize and Standardize the data

# visualizing the first 10 images in the dataset and their labels
%matplotlib inline
import matplotlib.pyplot as plt
plt.figure(figsize=(10, 1))
for i in range(10):
    plt.subplot(1, 10, i+1)
    plt.imshow(X_train[i], cmap="gray")
    plt.axis('off')
plt.show()
print('label for each of the above image: %s' % (y_train[0:10]))

label for each of the above image: [2 6 7 4 4 0 3 0 7 3]

X_train.shape

(42000, 32, 32)

y_train.shape

(42000,)

Need to reshape the X_train and X_test so that the same can be fed for model building. We need to feed a 2D tensor into the model and currently we have a 3D tensor.

• We will normalize the data. We divide by 255 as this is a grayscale image and can take values from 0-255

X_train = X_train.reshape(X_train.shape[0], 1024, 1)
X_test = X_test.reshape(X_test.shape[0], 1024, 1)

# # normalize inputs from 0-255 to 0-1
X_train = X_train / 255.0
X_test = X_test / 255.0

print('Resized Training set', X_train.shape, y_train.shape)
print('Resized Test set', X_test.shape, y_test.shape)

Resized Training set (42000, 1024, 1) (42000,)
Resized Test set (18000, 1024, 1) (18000,)

Encoding the target variables. We need to one hot encode the labels for the model to understand the labels better. We will be using categorical cross entropy as our loss function and for this purpose we need our labels to be in one hot encoded format.

from tensorflow.keras.utils import to_categorical
# one hot encode outputs
y_train = to_categorical(y_train)
y_test = to_categorical(y_test)

# no.of classes
num_classes = y_test.shape[1] 
print("The number of classes in this dataset are:",num_classes)

The number of classes in this dataset are: 10

Model building

# define model

from tensorflow.keras import optimizers
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Flatten

def nn_model():
    # create model
    model = Sequential()  
    model.add(Flatten())
    model.add(Dense(256, activation='relu')) ###Multiple Dense units with Relu activation
    model.add(Dense(64, activation='relu'))
    model.add(Dense(64, activation='relu'))
    model.add(Dense(32, activation='relu'))
    model.add(Dense(num_classes, activation='softmax'))
    return model

# build the model
model = nn_model()

# Compile model
sgd = optimizers.Adam(lr=1e-3)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy']) ### Loss function = Categorical cross entropy

# Fit the model
training_history = model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=200, batch_size=300, verbose=2)

Epoch 1/200
140/140 - 2s - loss: 2.3023 - accuracy: 0.1104 - val_loss: 2.2763 - val_accuracy: 0.1602
Epoch 2/200
140/140 - 1s - loss: 2.1142 - accuracy: 0.2288 - val_loss: 1.9043 - val_accuracy: 0.3217
Epoch 3/200
140/140 - 1s - loss: 1.7991 - accuracy: 0.3743 - val_loss: 1.6100 - val_accuracy: 0.4541
Epoch 4/200
140/140 - 1s - loss: 1.5231 - accuracy: 0.4901 - val_loss: 1.4489 - val_accuracy: 0.5077
Epoch 5/200
140/140 - 1s - loss: 1.3782 - accuracy: 0.5453 - val_loss: 1.3027 - val_accuracy: 0.5718
Epoch 6/200
140/140 - 1s - loss: 1.3049 - accuracy: 0.5741 - val_loss: 1.2819 - val_accuracy: 0.5788
Epoch 7/200
140/140 - 1s - loss: 1.2354 - accuracy: 0.6001 - val_loss: 1.2186 - val_accuracy: 0.6030
Epoch 8/200
140/140 - 1s - loss: 1.2025 - accuracy: 0.6098 - val_loss: 1.1725 - val_accuracy: 0.6238
Epoch 9/200
140/140 - 1s - loss: 1.1371 - accuracy: 0.6385 - val_loss: 1.1106 - val_accuracy: 0.6502
Epoch 10/200
140/140 - 1s - loss: 1.0831 - accuracy: 0.6580 - val_loss: 1.0579 - val_accuracy: 0.6671
Epoch 11/200
140/140 - 1s - loss: 1.0274 - accuracy: 0.6819 - val_loss: 1.0129 - val_accuracy: 0.6901
Epoch 12/200
140/140 - 1s - loss: 0.9906 - accuracy: 0.6955 - val_loss: 1.0500 - val_accuracy: 0.6724
Epoch 13/200
140/140 - 1s - loss: 0.9637 - accuracy: 0.7024 - val_loss: 0.9794 - val_accuracy: 0.7000
Epoch 14/200
140/140 - 1s - loss: 0.9373 - accuracy: 0.7110 - val_loss: 0.9505 - val_accuracy: 0.7086
Epoch 15/200
140/140 - 1s - loss: 0.9081 - accuracy: 0.7224 - val_loss: 0.9236 - val_accuracy: 0.7202
Epoch 16/200
140/140 - 1s - loss: 0.8899 - accuracy: 0.7273 - val_loss: 0.9027 - val_accuracy: 0.7278
Epoch 17/200
140/140 - 1s - loss: 0.8704 - accuracy: 0.7329 - val_loss: 0.8807 - val_accuracy: 0.7363
Epoch 18/200
140/140 - 1s - loss: 0.8510 - accuracy: 0.7389 - val_loss: 0.8703 - val_accuracy: 0.7347
Epoch 19/200
140/140 - 1s - loss: 0.8514 - accuracy: 0.7347 - val_loss: 0.8711 - val_accuracy: 0.7344
Epoch 20/200
140/140 - 1s - loss: 0.8278 - accuracy: 0.7448 - val_loss: 0.8476 - val_accuracy: 0.7417
Epoch 21/200
140/140 - 1s - loss: 0.8063 - accuracy: 0.7529 - val_loss: 0.8567 - val_accuracy: 0.7408
Epoch 22/200
140/140 - 1s - loss: 0.7890 - accuracy: 0.7595 - val_loss: 0.8588 - val_accuracy: 0.7433
Epoch 23/200
140/140 - 1s - loss: 0.7865 - accuracy: 0.7587 - val_loss: 0.8366 - val_accuracy: 0.7499
Epoch 24/200
140/140 - 1s - loss: 0.7664 - accuracy: 0.7631 - val_loss: 0.8367 - val_accuracy: 0.7438
Epoch 25/200
140/140 - 1s - loss: 0.7621 - accuracy: 0.7650 - val_loss: 0.8245 - val_accuracy: 0.7537
Epoch 26/200
140/140 - 1s - loss: 0.7508 - accuracy: 0.7689 - val_loss: 0.7958 - val_accuracy: 0.7623
Epoch 27/200
140/140 - 1s - loss: 0.7361 - accuracy: 0.7715 - val_loss: 0.7758 - val_accuracy: 0.7659
Epoch 28/200
140/140 - 1s - loss: 0.7344 - accuracy: 0.7734 - val_loss: 0.8124 - val_accuracy: 0.7534
Epoch 29/200
140/140 - 1s - loss: 0.7287 - accuracy: 0.7749 - val_loss: 0.7732 - val_accuracy: 0.7683
Epoch 30/200
140/140 - 1s - loss: 0.7056 - accuracy: 0.7798 - val_loss: 0.7689 - val_accuracy: 0.7700
Epoch 31/200
140/140 - 1s - loss: 0.6912 - accuracy: 0.7859 - val_loss: 0.7631 - val_accuracy: 0.7716
Epoch 32/200
140/140 - 1s - loss: 0.6878 - accuracy: 0.7866 - val_loss: 0.7878 - val_accuracy: 0.7644
Epoch 33/200
140/140 - 1s - loss: 0.6891 - accuracy: 0.7866 - val_loss: 0.7904 - val_accuracy: 0.7648
Epoch 34/200
140/140 - 1s - loss: 0.6817 - accuracy: 0.7891 - val_loss: 0.7935 - val_accuracy: 0.7641
Epoch 35/200
140/140 - 1s - loss: 0.6689 - accuracy: 0.7916 - val_loss: 0.7354 - val_accuracy: 0.7823
Epoch 36/200
140/140 - 1s - loss: 0.6542 - accuracy: 0.7994 - val_loss: 0.7325 - val_accuracy: 0.7835
Epoch 37/200
140/140 - 1s - loss: 0.6521 - accuracy: 0.7980 - val_loss: 0.7546 - val_accuracy: 0.7743
Epoch 38/200
140/140 - 1s - loss: 0.6540 - accuracy: 0.7969 - val_loss: 0.7449 - val_accuracy: 0.7787
Epoch 39/200
140/140 - 1s - loss: 0.6346 - accuracy: 0.8025 - val_loss: 0.7446 - val_accuracy: 0.7795
Epoch 40/200
140/140 - 1s - loss: 0.6259 - accuracy: 0.8078 - val_loss: 0.7372 - val_accuracy: 0.7838
Epoch 41/200
140/140 - 1s - loss: 0.6215 - accuracy: 0.8081 - val_loss: 0.7326 - val_accuracy: 0.7840
Epoch 42/200
140/140 - 1s - loss: 0.6136 - accuracy: 0.8112 - val_loss: 0.7062 - val_accuracy: 0.7917
Epoch 43/200
140/140 - 1s - loss: 0.6174 - accuracy: 0.8087 - val_loss: 0.7058 - val_accuracy: 0.7909
Epoch 44/200
140/140 - 1s - loss: 0.6070 - accuracy: 0.8104 - val_loss: 0.7349 - val_accuracy: 0.7850
Epoch 45/200
140/140 - 1s - loss: 0.5991 - accuracy: 0.8139 - val_loss: 0.7529 - val_accuracy: 0.7763
Epoch 46/200
140/140 - 1s - loss: 0.6089 - accuracy: 0.8103 - val_loss: 0.7171 - val_accuracy: 0.7879
Epoch 47/200
140/140 - 1s - loss: 0.5991 - accuracy: 0.8138 - val_loss: 0.7583 - val_accuracy: 0.7737
Epoch 48/200
140/140 - 1s - loss: 0.5899 - accuracy: 0.8157 - val_loss: 0.7317 - val_accuracy: 0.7853
Epoch 49/200
140/140 - 1s - loss: 0.5766 - accuracy: 0.8194 - val_loss: 0.7186 - val_accuracy: 0.7889
Epoch 50/200
140/140 - 1s - loss: 0.5763 - accuracy: 0.8186 - val_loss: 0.7177 - val_accuracy: 0.7878
Epoch 51/200
140/140 - 1s - loss: 0.5690 - accuracy: 0.8230 - val_loss: 0.7370 - val_accuracy: 0.7839
Epoch 52/200
140/140 - 1s - loss: 0.5694 - accuracy: 0.8216 - val_loss: 0.7028 - val_accuracy: 0.7951
Epoch 53/200
140/140 - 1s - loss: 0.5660 - accuracy: 0.8236 - val_loss: 0.7158 - val_accuracy: 0.7918
Epoch 54/200
140/140 - 1s - loss: 0.5570 - accuracy: 0.8260 - val_loss: 0.7537 - val_accuracy: 0.7779
Epoch 55/200
140/140 - 1s - loss: 0.5630 - accuracy: 0.8233 - val_loss: 0.6872 - val_accuracy: 0.8007
Epoch 56/200
140/140 - 1s - loss: 0.5528 - accuracy: 0.8268 - val_loss: 0.7172 - val_accuracy: 0.7881
Epoch 57/200
140/140 - 1s - loss: 0.5419 - accuracy: 0.8297 - val_loss: 0.7227 - val_accuracy: 0.7885
Epoch 58/200
140/140 - 1s - loss: 0.5353 - accuracy: 0.8305 - val_loss: 0.6836 - val_accuracy: 0.8016
Epoch 59/200
140/140 - 1s - loss: 0.5334 - accuracy: 0.8330 - val_loss: 0.6838 - val_accuracy: 0.8023
Epoch 60/200
140/140 - 1s - loss: 0.5364 - accuracy: 0.8310 - val_loss: 0.7086 - val_accuracy: 0.7931
Epoch 61/200
140/140 - 1s - loss: 0.5322 - accuracy: 0.8324 - val_loss: 0.6940 - val_accuracy: 0.7983
Epoch 62/200
140/140 - 1s - loss: 0.5251 - accuracy: 0.8371 - val_loss: 0.6903 - val_accuracy: 0.8002
Epoch 63/200
140/140 - 1s - loss: 0.5151 - accuracy: 0.8380 - val_loss: 0.6828 - val_accuracy: 0.8021
Epoch 64/200
140/140 - 1s - loss: 0.5183 - accuracy: 0.8370 - val_loss: 0.7257 - val_accuracy: 0.7897
Epoch 65/200
140/140 - 1s - loss: 0.5235 - accuracy: 0.8360 - val_loss: 0.7005 - val_accuracy: 0.7987
Epoch 66/200
140/140 - 1s - loss: 0.5155 - accuracy: 0.8383 - val_loss: 0.7209 - val_accuracy: 0.7913
Epoch 67/200
140/140 - 1s - loss: 0.5103 - accuracy: 0.8393 - val_loss: 0.6745 - val_accuracy: 0.8050
Epoch 68/200
140/140 - 1s - loss: 0.5208 - accuracy: 0.8362 - val_loss: 0.6897 - val_accuracy: 0.8056
Epoch 69/200
140/140 - 1s - loss: 0.5146 - accuracy: 0.8375 - val_loss: 0.6884 - val_accuracy: 0.7987
Epoch 70/200
140/140 - 1s - loss: 0.4981 - accuracy: 0.8428 - val_loss: 0.6707 - val_accuracy: 0.8091
Epoch 71/200
140/140 - 1s - loss: 0.5033 - accuracy: 0.8412 - val_loss: 0.6967 - val_accuracy: 0.7987
Epoch 72/200
140/140 - 1s - loss: 0.4953 - accuracy: 0.8437 - val_loss: 0.6899 - val_accuracy: 0.8047
Epoch 73/200
140/140 - 1s - loss: 0.4908 - accuracy: 0.8454 - val_loss: 0.7099 - val_accuracy: 0.7991
Epoch 74/200
140/140 - 1s - loss: 0.4964 - accuracy: 0.8434 - val_loss: 0.6768 - val_accuracy: 0.8062
Epoch 75/200
140/140 - 1s - loss: 0.5015 - accuracy: 0.8427 - val_loss: 0.6892 - val_accuracy: 0.8035
Epoch 76/200
140/140 - 1s - loss: 0.4867 - accuracy: 0.8457 - val_loss: 0.6908 - val_accuracy: 0.8003
Epoch 77/200
140/140 - 1s - loss: 0.4827 - accuracy: 0.8482 - val_loss: 0.7009 - val_accuracy: 0.7974
Epoch 78/200
140/140 - 1s - loss: 0.4811 - accuracy: 0.8491 - val_loss: 0.6796 - val_accuracy: 0.8066
Epoch 79/200
140/140 - 1s - loss: 0.4809 - accuracy: 0.8467 - val_loss: 0.7113 - val_accuracy: 0.7984
Epoch 80/200
140/140 - 1s - loss: 0.4914 - accuracy: 0.8455 - val_loss: 0.7254 - val_accuracy: 0.7938
Epoch 81/200
140/140 - 1s - loss: 0.4767 - accuracy: 0.8503 - val_loss: 0.6861 - val_accuracy: 0.8044
Epoch 82/200
140/140 - 1s - loss: 0.4779 - accuracy: 0.8483 - val_loss: 0.6685 - val_accuracy: 0.8092
Epoch 83/200
140/140 - 1s - loss: 0.4632 - accuracy: 0.8540 - val_loss: 0.6852 - val_accuracy: 0.8030
Epoch 84/200
140/140 - 1s - loss: 0.4729 - accuracy: 0.8518 - val_loss: 0.7113 - val_accuracy: 0.7969
Epoch 85/200
140/140 - 1s - loss: 0.4693 - accuracy: 0.8504 - val_loss: 0.6752 - val_accuracy: 0.8097
Epoch 86/200
140/140 - 1s - loss: 0.4635 - accuracy: 0.8535 - val_loss: 0.6717 - val_accuracy: 0.8119
Epoch 87/200
140/140 - 1s - loss: 0.4589 - accuracy: 0.8559 - val_loss: 0.6798 - val_accuracy: 0.8084
Epoch 88/200
140/140 - 1s - loss: 0.4593 - accuracy: 0.8560 - val_loss: 0.6936 - val_accuracy: 0.8013
Epoch 89/200
140/140 - 1s - loss: 0.4519 - accuracy: 0.8575 - val_loss: 0.6732 - val_accuracy: 0.8127
Epoch 90/200
140/140 - 1s - loss: 0.4484 - accuracy: 0.8582 - val_loss: 0.6841 - val_accuracy: 0.8056
Epoch 91/200
140/140 - 1s - loss: 0.4556 - accuracy: 0.8569 - val_loss: 0.6825 - val_accuracy: 0.8096
Epoch 92/200
140/140 - 1s - loss: 0.4463 - accuracy: 0.8576 - val_loss: 0.6844 - val_accuracy: 0.8051
Epoch 93/200
140/140 - 1s - loss: 0.4400 - accuracy: 0.8615 - val_loss: 0.6847 - val_accuracy: 0.8052
Epoch 94/200
140/140 - 1s - loss: 0.4371 - accuracy: 0.8627 - val_loss: 0.6837 - val_accuracy: 0.8079
Epoch 95/200
140/140 - 1s - loss: 0.4480 - accuracy: 0.8589 - val_loss: 0.6947 - val_accuracy: 0.8034
Epoch 96/200
140/140 - 1s - loss: 0.4365 - accuracy: 0.8620 - val_loss: 0.7203 - val_accuracy: 0.7963
Epoch 97/200
140/140 - 1s - loss: 0.4376 - accuracy: 0.8622 - val_loss: 0.6827 - val_accuracy: 0.8107
Epoch 98/200
140/140 - 1s - loss: 0.4353 - accuracy: 0.8611 - val_loss: 0.6841 - val_accuracy: 0.8072
Epoch 99/200
140/140 - 1s - loss: 0.4287 - accuracy: 0.8654 - val_loss: 0.6712 - val_accuracy: 0.8123
Epoch 100/200
140/140 - 1s - loss: 0.4262 - accuracy: 0.8642 - val_loss: 0.6788 - val_accuracy: 0.8111
Epoch 101/200
140/140 - 1s - loss: 0.4319 - accuracy: 0.8635 - val_loss: 0.6791 - val_accuracy: 0.8112
Epoch 102/200
140/140 - 1s - loss: 0.4245 - accuracy: 0.8653 - val_loss: 0.6750 - val_accuracy: 0.8078
Epoch 103/200
140/140 - 1s - loss: 0.4315 - accuracy: 0.8639 - val_loss: 0.6741 - val_accuracy: 0.8119
Epoch 104/200
140/140 - 1s - loss: 0.4289 - accuracy: 0.8624 - val_loss: 0.6956 - val_accuracy: 0.8078
Epoch 105/200
140/140 - 1s - loss: 0.4219 - accuracy: 0.8669 - val_loss: 0.6752 - val_accuracy: 0.8096
Epoch 106/200
140/140 - 1s - loss: 0.4224 - accuracy: 0.8654 - val_loss: 0.7135 - val_accuracy: 0.7967
Epoch 107/200
140/140 - 1s - loss: 0.4105 - accuracy: 0.8702 - val_loss: 0.6760 - val_accuracy: 0.8121
Epoch 108/200
140/140 - 1s - loss: 0.4133 - accuracy: 0.8684 - val_loss: 0.6940 - val_accuracy: 0.8096
Epoch 109/200
140/140 - 1s - loss: 0.4152 - accuracy: 0.8694 - val_loss: 0.7060 - val_accuracy: 0.8039
Epoch 110/200
140/140 - 1s - loss: 0.4079 - accuracy: 0.8711 - val_loss: 0.6600 - val_accuracy: 0.8195
Epoch 111/200
140/140 - 1s - loss: 0.4056 - accuracy: 0.8708 - val_loss: 0.7221 - val_accuracy: 0.7982
Epoch 112/200
140/140 - 1s - loss: 0.4128 - accuracy: 0.8695 - val_loss: 0.6626 - val_accuracy: 0.8189
Epoch 113/200
140/140 - 1s - loss: 0.4044 - accuracy: 0.8706 - val_loss: 0.6848 - val_accuracy: 0.8123
Epoch 114/200
140/140 - 1s - loss: 0.4044 - accuracy: 0.8717 - val_loss: 0.7006 - val_accuracy: 0.8076
Epoch 115/200
140/140 - 1s - loss: 0.4067 - accuracy: 0.8687 - val_loss: 0.6838 - val_accuracy: 0.8164
Epoch 116/200
140/140 - 1s - loss: 0.4026 - accuracy: 0.8727 - val_loss: 0.7112 - val_accuracy: 0.8027
Epoch 117/200
140/140 - 1s - loss: 0.4029 - accuracy: 0.8719 - val_loss: 0.6856 - val_accuracy: 0.8126
Epoch 118/200
140/140 - 1s - loss: 0.3879 - accuracy: 0.8768 - val_loss: 0.6912 - val_accuracy: 0.8096
Epoch 119/200
140/140 - 1s - loss: 0.3965 - accuracy: 0.8735 - val_loss: 0.7080 - val_accuracy: 0.8025
Epoch 120/200
140/140 - 1s - loss: 0.3962 - accuracy: 0.8726 - val_loss: 0.6906 - val_accuracy: 0.8119
Epoch 121/200
140/140 - 1s - loss: 0.3927 - accuracy: 0.8745 - val_loss: 0.6708 - val_accuracy: 0.8182
Epoch 122/200
140/140 - 1s - loss: 0.3884 - accuracy: 0.8759 - val_loss: 0.7086 - val_accuracy: 0.8073
Epoch 123/200
140/140 - 1s - loss: 0.3900 - accuracy: 0.8753 - val_loss: 0.7119 - val_accuracy: 0.8097
Epoch 124/200
140/140 - 1s - loss: 0.3815 - accuracy: 0.8791 - val_loss: 0.6969 - val_accuracy: 0.8123
Epoch 125/200
140/140 - 1s - loss: 0.3841 - accuracy: 0.8766 - val_loss: 0.7016 - val_accuracy: 0.8104
Epoch 126/200
140/140 - 1s - loss: 0.3865 - accuracy: 0.8780 - val_loss: 0.7037 - val_accuracy: 0.8126
Epoch 127/200
140/140 - 1s - loss: 0.3814 - accuracy: 0.8783 - val_loss: 0.7087 - val_accuracy: 0.8085
Epoch 128/200
140/140 - 1s - loss: 0.3880 - accuracy: 0.8758 - val_loss: 0.7425 - val_accuracy: 0.7987
Epoch 129/200
140/140 - 1s - loss: 0.3827 - accuracy: 0.8774 - val_loss: 0.6749 - val_accuracy: 0.8179
Epoch 130/200
140/140 - 1s - loss: 0.3779 - accuracy: 0.8780 - val_loss: 0.6948 - val_accuracy: 0.8137
Epoch 131/200
140/140 - 1s - loss: 0.3812 - accuracy: 0.8787 - val_loss: 0.6963 - val_accuracy: 0.8108
Epoch 132/200
140/140 - 1s - loss: 0.3765 - accuracy: 0.8793 - val_loss: 0.7099 - val_accuracy: 0.8118
Epoch 133/200
140/140 - 1s - loss: 0.3793 - accuracy: 0.8798 - val_loss: 0.6915 - val_accuracy: 0.8152
Epoch 134/200
140/140 - 1s - loss: 0.3720 - accuracy: 0.8806 - val_loss: 0.7146 - val_accuracy: 0.8107
Epoch 135/200
140/140 - 1s - loss: 0.3613 - accuracy: 0.8857 - val_loss: 0.7431 - val_accuracy: 0.8012
Epoch 136/200
140/140 - 1s - loss: 0.3743 - accuracy: 0.8810 - val_loss: 0.7104 - val_accuracy: 0.8066
Epoch 137/200
140/140 - 1s - loss: 0.3697 - accuracy: 0.8818 - val_loss: 0.7098 - val_accuracy: 0.8099
Epoch 138/200
140/140 - 1s - loss: 0.3716 - accuracy: 0.8809 - val_loss: 0.7418 - val_accuracy: 0.8041
Epoch 139/200
140/140 - 1s - loss: 0.3716 - accuracy: 0.8799 - val_loss: 0.7155 - val_accuracy: 0.8087
Epoch 140/200
140/140 - 1s - loss: 0.3678 - accuracy: 0.8820 - val_loss: 0.7416 - val_accuracy: 0.7994
Epoch 141/200
140/140 - 1s - loss: 0.3591 - accuracy: 0.8845 - val_loss: 0.7095 - val_accuracy: 0.8152
Epoch 142/200
140/140 - 1s - loss: 0.3641 - accuracy: 0.8823 - val_loss: 0.7431 - val_accuracy: 0.8009
Epoch 143/200
140/140 - 1s - loss: 0.3667 - accuracy: 0.8825 - val_loss: 0.7059 - val_accuracy: 0.8101
Epoch 144/200
140/140 - 1s - loss: 0.3680 - accuracy: 0.8824 - val_loss: 0.7118 - val_accuracy: 0.8128
Epoch 145/200
140/140 - 1s - loss: 0.3533 - accuracy: 0.8865 - val_loss: 0.7110 - val_accuracy: 0.8131
Epoch 146/200
140/140 - 1s - loss: 0.3566 - accuracy: 0.8846 - val_loss: 0.7222 - val_accuracy: 0.8117
Epoch 147/200
140/140 - 1s - loss: 0.3487 - accuracy: 0.8878 - val_loss: 0.7036 - val_accuracy: 0.8128
Epoch 148/200
140/140 - 1s - loss: 0.3659 - accuracy: 0.8828 - val_loss: 0.7263 - val_accuracy: 0.8089
Epoch 149/200
140/140 - 1s - loss: 0.3522 - accuracy: 0.8870 - val_loss: 0.7353 - val_accuracy: 0.8095
Epoch 150/200
140/140 - 1s - loss: 0.3624 - accuracy: 0.8830 - val_loss: 0.7330 - val_accuracy: 0.8088
Epoch 151/200
140/140 - 1s - loss: 0.3453 - accuracy: 0.8892 - val_loss: 0.7537 - val_accuracy: 0.8061
Epoch 152/200
140/140 - 1s - loss: 0.3478 - accuracy: 0.8884 - val_loss: 0.7264 - val_accuracy: 0.8101
Epoch 153/200
140/140 - 1s - loss: 0.3560 - accuracy: 0.8840 - val_loss: 0.7188 - val_accuracy: 0.8141
Epoch 154/200
140/140 - 1s - loss: 0.3460 - accuracy: 0.8898 - val_loss: 0.7383 - val_accuracy: 0.8102
Epoch 155/200
140/140 - 1s - loss: 0.3508 - accuracy: 0.8867 - val_loss: 0.7158 - val_accuracy: 0.8137
Epoch 156/200
140/140 - 1s - loss: 0.3449 - accuracy: 0.8894 - val_loss: 0.7126 - val_accuracy: 0.8158
Epoch 157/200
140/140 - 1s - loss: 0.3451 - accuracy: 0.8887 - val_loss: 0.7130 - val_accuracy: 0.8181
Epoch 158/200
140/140 - 1s - loss: 0.3479 - accuracy: 0.8881 - val_loss: 0.7152 - val_accuracy: 0.8158
Epoch 159/200
140/140 - 1s - loss: 0.3341 - accuracy: 0.8920 - val_loss: 0.7235 - val_accuracy: 0.8146
Epoch 160/200
140/140 - 1s - loss: 0.3483 - accuracy: 0.8874 - val_loss: 0.7354 - val_accuracy: 0.8103
Epoch 161/200
140/140 - 1s - loss: 0.3373 - accuracy: 0.8925 - val_loss: 0.7367 - val_accuracy: 0.8111
Epoch 162/200
140/140 - 1s - loss: 0.3445 - accuracy: 0.8893 - val_loss: 0.7352 - val_accuracy: 0.8082
Epoch 163/200
140/140 - 1s - loss: 0.3356 - accuracy: 0.8924 - val_loss: 0.7180 - val_accuracy: 0.8153
Epoch 164/200
140/140 - 1s - loss: 0.3307 - accuracy: 0.8947 - val_loss: 0.7314 - val_accuracy: 0.8148
Epoch 165/200
140/140 - 1s - loss: 0.3375 - accuracy: 0.8910 - val_loss: 0.7347 - val_accuracy: 0.8149
Epoch 166/200
140/140 - 1s - loss: 0.3352 - accuracy: 0.8914 - val_loss: 0.7227 - val_accuracy: 0.8139
Epoch 167/200
140/140 - 1s - loss: 0.3391 - accuracy: 0.8901 - val_loss: 0.7479 - val_accuracy: 0.8092
Epoch 168/200
140/140 - 1s - loss: 0.3467 - accuracy: 0.8864 - val_loss: 0.7328 - val_accuracy: 0.8130
Epoch 169/200
140/140 - 1s - loss: 0.3356 - accuracy: 0.8930 - val_loss: 0.7183 - val_accuracy: 0.8166
Epoch 170/200
140/140 - 1s - loss: 0.3366 - accuracy: 0.8912 - val_loss: 0.7396 - val_accuracy: 0.8113
Epoch 171/200
140/140 - 1s - loss: 0.3217 - accuracy: 0.8960 - val_loss: 0.7355 - val_accuracy: 0.8107
Epoch 172/200
140/140 - 1s - loss: 0.3268 - accuracy: 0.8940 - val_loss: 0.7295 - val_accuracy: 0.8177
Epoch 173/200
140/140 - 1s - loss: 0.3252 - accuracy: 0.8965 - val_loss: 0.7371 - val_accuracy: 0.8126
Epoch 174/200
140/140 - 1s - loss: 0.3378 - accuracy: 0.8901 - val_loss: 0.7323 - val_accuracy: 0.8154
Epoch 175/200
140/140 - 1s - loss: 0.3295 - accuracy: 0.8940 - val_loss: 0.7431 - val_accuracy: 0.8129
Epoch 176/200
140/140 - 1s - loss: 0.3223 - accuracy: 0.8951 - val_loss: 0.7532 - val_accuracy: 0.8123
Epoch 177/200
140/140 - 1s - loss: 0.3349 - accuracy: 0.8931 - val_loss: 0.7645 - val_accuracy: 0.8079
Epoch 178/200
140/140 - 1s - loss: 0.3227 - accuracy: 0.8973 - val_loss: 0.7397 - val_accuracy: 0.8174
Epoch 179/200
140/140 - 1s - loss: 0.3259 - accuracy: 0.8935 - val_loss: 0.7464 - val_accuracy: 0.8097
Epoch 180/200
140/140 - 1s - loss: 0.3292 - accuracy: 0.8932 - val_loss: 0.7405 - val_accuracy: 0.8194
Epoch 181/200
140/140 - 1s - loss: 0.3211 - accuracy: 0.8962 - val_loss: 0.7475 - val_accuracy: 0.8140
Epoch 182/200
140/140 - 1s - loss: 0.3226 - accuracy: 0.8950 - val_loss: 0.7502 - val_accuracy: 0.8134
Epoch 183/200
140/140 - 1s - loss: 0.3289 - accuracy: 0.8930 - val_loss: 0.7510 - val_accuracy: 0.8129
Epoch 184/200
140/140 - 1s - loss: 0.3114 - accuracy: 0.8997 - val_loss: 0.7684 - val_accuracy: 0.8122
Epoch 185/200
140/140 - 1s - loss: 0.3247 - accuracy: 0.8958 - val_loss: 0.7831 - val_accuracy: 0.8051
Epoch 186/200
140/140 - 1s - loss: 0.3224 - accuracy: 0.8944 - val_loss: 0.7760 - val_accuracy: 0.8052
Epoch 187/200
140/140 - 1s - loss: 0.3185 - accuracy: 0.8961 - val_loss: 0.7377 - val_accuracy: 0.8177
Epoch 188/200
140/140 - 1s - loss: 0.3172 - accuracy: 0.8971 - val_loss: 0.7420 - val_accuracy: 0.8149
Epoch 189/200
140/140 - 1s - loss: 0.3079 - accuracy: 0.9011 - val_loss: 0.7547 - val_accuracy: 0.8166
Epoch 190/200
140/140 - 1s - loss: 0.3280 - accuracy: 0.8921 - val_loss: 0.7568 - val_accuracy: 0.8109
Epoch 191/200
140/140 - 1s - loss: 0.3132 - accuracy: 0.8991 - val_loss: 0.7684 - val_accuracy: 0.8146
Epoch 192/200
140/140 - 1s - loss: 0.3135 - accuracy: 0.8984 - val_loss: 0.7337 - val_accuracy: 0.8192
Epoch 193/200
140/140 - 1s - loss: 0.3132 - accuracy: 0.8974 - val_loss: 0.7523 - val_accuracy: 0.8157
Epoch 194/200
140/140 - 1s - loss: 0.3086 - accuracy: 0.8999 - val_loss: 0.7454 - val_accuracy: 0.8154
Epoch 195/200
140/140 - 1s - loss: 0.3128 - accuracy: 0.8989 - val_loss: 0.7744 - val_accuracy: 0.8084
Epoch 196/200
140/140 - 1s - loss: 0.3230 - accuracy: 0.8926 - val_loss: 0.7464 - val_accuracy: 0.8179
Epoch 197/200
140/140 - 1s - loss: 0.3027 - accuracy: 0.9037 - val_loss: 0.7633 - val_accuracy: 0.8141
Epoch 198/200
140/140 - 1s - loss: 0.3107 - accuracy: 0.9008 - val_loss: 0.8033 - val_accuracy: 0.8051
Epoch 199/200
140/140 - 1s - loss: 0.3074 - accuracy: 0.9011 - val_loss: 0.7538 - val_accuracy: 0.8150
Epoch 200/200
140/140 - 1s - loss: 0.3159 - accuracy: 0.8975 - val_loss: 0.7896 - val_accuracy: 0.8078

Conclusion and Interpretation

# Final evaluation of the model
scores = model.evaluate(X_test, y_test, verbose=1)
print("Loss:", scores[0])
print("Accuracy:", scores[1])

563/563 [==============================] - 1s 1ms/step - loss: 0.7896 - accuracy: 0.8078
Loss: 0.7895674109458923
Accuracy: 0.8077777624130249

accuracy      = training_history.history['accuracy']
val_accuracy  = training_history.history['val_accuracy']
loss     = training_history.history['loss']
val_loss = training_history.history['val_loss']

epochs   = range(len(accuracy)) # Get number of epochs

plt.plot  ( epochs, accuracy, label = 'training accuracy' )
plt.plot  ( epochs, val_accuracy, label = 'validation accuracy' )
plt.title ('Training and validation accuracy')
plt.legend(loc = 'lower right')
plt.figure()

plt.plot  ( epochs, loss, label = 'training loss' )
plt.plot  ( epochs, val_loss, label = 'validation loss' )
plt.legend(loc = 'upper right')
plt.title ('Training and validation loss'   )

Text(0.5, 1.0, 'Training and validation loss')

print('Trianing accuracy',max(accuracy))
print('Validation accuracy',max(val_accuracy))

Trianing accuracy 0.9037142992019653
Validation accuracy 0.8195000290870667

There are around 10 classes in the dataset which represent digits from 0-9.

We tried training a Neural Network with dense hidden layers of different number of units and are able to achieve a final test accuracy of 80.77 %.

Also we notice that after a certain point the model begins to overfit on our dataset as is clear from the plots above where the validation loss begins to increase after certain point and validation accuracy begins to decrease.

Thus, with this amount of accuracy we are able to distinguish between the different digits in this dataset.